temp hacking

Support using Pipecat turn detection instead of OpenAI Realtime API turn detection

.github/workflows/format.yaml

@@ -38,4 +38,4 @@ jobs:
         id: ruff
         run: |
           source .venv/bin/activate
-          ruff format --config line-length=100 --diff --exclude "*_pb2.py"
+          ruff format --diff

.gitignore

@@ -4,6 +4,7 @@ __pycache__/
 *~
 venv
 .venv
+/.idea
 #*#
 
 # Distribution / packaging

CHANGELOG.md

@@ -5,6 +5,143 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+
+### Added
+
+- Added `GatedOpenAILLMContextAggregator`. This aggregator keeps the last
+  received OpenAI LLM context frame and it doesn't let it through until the
+  notifier is notified.
+
+- Added `WakeNotifierFilter`. This processor expects a list of frame types and
+  will execute a given callback predicate when a frame of any of those type is
+  being processed. If the callback returns true the notifier will be notified.
+
+- Added `NullFilter`. A null filter doesn't push any frames upstream or
+  downstream. This is usually used to disable one of the pipelines in
+  `ParallelPipeline`.
+
+- Added `EventNotifier`. This can be used as a very simple synchronization
+  feature between processors.
+
+- Added `TavusVideoService`. This is an integration for Tavus digital twins.
+  (see https://www.tavus.io/)
+
+- Added `DailyTransport.update_subscriptions()`. This allows you to have fine
+  grained control of what media subscriptions you want for each participant in a
+  room.
+
+### Changed
+
+- The following `DailyTransport` functions are now `async` which means they need
+  to be awaited: `start_dialout`, `stop_dialout`, `start_recording`,
+  `stop_recording`, `capture_participant_transcription` and
+  `capture_participant_video`.
+
+- Changed default output sample rate to 24000. This changes all TTS service to
+  output to 24000 and also the default output transport sample rate. This
+  improves audio quality at the cost of some extra bandwidth.
+
+### Fixed
+
+- Improved bot speaking detection for all TTS services by using actual bot
+  audio.
+
+- Fixed an issue that was generating constant bot started/stopped speaking
+  frames for HTTP TTS services.
+
+- Fixed an issue that was causing stuttering with AWS TTS service.
+
+- Fixed an issue with PlayHTTTSService, where the TTFB metrics were reporting
+  very small time values.
+
+### Other
+
+- Added a new foundational example 22-natural-conversation.py. This examples
+  shows how to achieve a more natural conversation detecting when the user ends
+  statement.
+
+## [0.0.47] - 2024-10-22
+
+### Added
+
+- Added `AssemblyAISTTService` and corresponding foundational examples
+  `07o-interruptible-assemblyai.py` and `13d-assemblyai-transcription.py`.
+
+- Added a foundational example for Gladia transcription:
+  `13c-gladia-transcription.py`
+
+### Changed
+
+- Updated `GladiaSTTService` to use the V2 API.
+
+- Changed `DailyTransport` transcription model to `nova-2-general`.
+
+### Fixed
+
+- Fixed an issue that would cause an import error when importing
+  `SileroVADAnalyzer` from the old package `pipecat.vad.silero`.
+
+- Fixed `enable_usage_metrics` to control LLM/TTS usage metrics separately
+  from `enable_metrics`.
+
+## [0.0.46] - 2024-10-19
+
+### Added
+
+- Added `audio_passthrough` parameter to `STTService`. If enabled it allows
+  audio frames to be pushed downstream in case other processors need them.
+
+- Added input parameter options for `PlayHTTTSService` and
+  `PlayHTHttpTTSService`.
+
+### Changed
+
+- Changed `DeepgramSTTService` model to `nova-2-general`.
+
+- Moved `SileroVAD` audio processor to `processors.audio.vad`.
+
+- Module `utils.audio` is now `audio.utils`. A new `resample_audio` function has
+  been added.
+
+- `PlayHTTTSService` now uses PlayHT websockets instead of HTTP requests.
+
+- The previous `PlayHTTTSService` HTTP implementation is now
+  `PlayHTHttpTTSService`.
+
+- `PlayHTTTSService` and `PlayHTHttpTTSService` now use a `voice_engine` of
+  `PlayHT3.0-mini`, which allows for multi-lingual support.
+
+- Renamed `OpenAILLMServiceRealtimeBeta` to `OpenAIRealtimeBetaLLMService` to
+  match other services.
+
+### Deprecated
+
+- `LLMUserResponseAggregator` and `LLMAssistantResponseAggregator` are
+  mostly deprecated, use `OpenAILLMContext` instead.
+
+- The `vad` package is now deprecated and `audio.vad` should be used
+  instead. The `avd` package will get removed in a future release.
+
+### Fixed
+
+- Fixed an issue that would cause an error if no VAD analyzer was passed to
+  `LiveKitTransport` params.
+
+- Fixed `SileroVAD` processor to support interruptions properly.
+
+### Other
+
+- Added `examples/foundational/07-interruptible-vad.py`. This is the same as
+  `07-interruptible.py` but using the `SileroVAD` processor instead of passing
+  the `VADAnalyzer` in the transport.
+
+## [0.0.45] - 2024-10-16
+
+### Changed
+
+- Metrics messages have moved out from the transport's base output into RTVI.
+
 ## [0.0.44] - 2024-10-15
 
 ### Added

README.md

@@ -38,7 +38,7 @@ pip install "pipecat-ai[option,...]"
 
 Your project may or may not need these, so they're made available as optional requirements. Here is a list:
 
-- **AI services**: `anthropic`, `aws`, `azure`, `deepgram`, `gladia`, `google`, `fal`, `lmnt`, `moondream`, `openai`, `openpipe`, `playht`, `silero`, `whisper`, `xtts`
+- **AI services**: `anthropic`, `assemblyai`, `aws`, `azure`, `deepgram`, `gladia`, `google`, `fal`, `lmnt`, `moondream`, `openai`, `openpipe`, `playht`, `silero`, `whisper`, `xtts`
 - **Transports**: `local`, `websocket`, `daily`
 
 ## Code examples
@@ -51,10 +51,7 @@ Your project may or may not need these, so they're made available as optional re
 Here is a very basic Pipecat bot that greets a user when they join a real-time session. We'll use [Daily](https://daily.co) for real-time media transport, and [Cartesia](https://cartesia.ai/) for text-to-speech.
 
 ```python
-#app.py
-
 import asyncio
-import aiohttp
 
 from pipecat.frames.frames import EndFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -64,39 +61,43 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
 
 async def main():
-  async with aiohttp.ClientSession() as session:
-    # Use Daily as a real-time media transport (WebRTC)
-    transport = DailyTransport(
-      room_url=...,
-      token=...,
-      bot_name="Bot Name",
-      params=DailyParams(audio_out_enabled=True))
+  # Use Daily as a real-time media transport (WebRTC)
+  transport = DailyTransport(
+    room_url=...,
+    token="", # leave empty. Note: token is _not_ your api key
+    bot_name="Bot Name",
+    params=DailyParams(audio_out_enabled=True))
 
-    # Use Cartesia for Text-to-Speech
-    tts = CartesiaTTSService(
-        api_key=...,
-        voice_id=...
-      )
+  # Use Cartesia for Text-to-Speech
+  tts = CartesiaTTSService(
+    api_key=...,
+    voice_id=...
+  )
 
-    # Simple pipeline that will process text to speech and output the result
-    pipeline = Pipeline([tts, transport.output()])
+  # Simple pipeline that will process text to speech and output the result
+  pipeline = Pipeline([tts, transport.output()])
 
-    # Create Pipecat processor that can run one or more pipelines tasks
-    runner = PipelineRunner()
+  # Create Pipecat processor that can run one or more pipelines tasks
+  runner = PipelineRunner()
 
-    # Assign the task callable to run the pipeline
-    task = PipelineTask(pipeline)
+  # Assign the task callable to run the pipeline
+  task = PipelineTask(pipeline)
 
-    # Register an event handler to play audio when a
-    # participant joins the transport WebRTC session
-    @transport.event_handler("on_participant_joined")
-    async def on_new_participant_joined(transport, participant):
-      participant_name = participant["info"]["userName"] or ''
-      # Queue a TextFrame that will get spoken by the TTS service (Cartesia)
-      await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
+  # Register an event handler to play audio when a
+  # participant joins the transport WebRTC session
+  @transport.event_handler("on_first_participant_joined")
+  async def on_first_participant_joined(transport, participant):
+    participant_name = participant.get("info", {}).get("userName", "")
+    # Queue a TextFrame that will get spoken by the TTS service (Cartesia)
+    await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
 
-    # Run the pipeline task
-    await runner.run(task)
+  # Register an event handler to exit the application when the user leaves.
+  @transport.event_handler("on_participant_left")
+  async def on_participant_left(transport, participant, reason):
+    await task.queue_frame(EndFrame())
+
+  # Run the pipeline task
+  await runner.run(task)
 
 if __name__ == "__main__":
   asyncio.run(main())
@@ -177,7 +178,7 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
   :ensure t
   :hook ((python-mode . lazy-ruff-mode))
   :config
-  (setq lazy-ruff-format-command "ruff format --config line-length=100")
+  (setq lazy-ruff-format-command "ruff format")
   (setq lazy-ruff-only-format-block t)
   (setq lazy-ruff-only-format-region t)
   (setq lazy-ruff-only-format-buffer t))
@@ -196,14 +197,13 @@ You can use [use-package](https://github.com/jwiegley/use-package) to install [e
 ### Visual Studio Code
 
 Install the
-[Ruff](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, enable formatting on save and configure `ruff` arguments:
+[Ruff](https://marketplace.visualstudio.com/items?itemName=charliermarsh.ruff) extension. Then edit the user settings (_Ctrl-Shift-P_ `Open User Settings (JSON)`) and set it as the default Python formatter, and enable formatting on save:
 
 ```json
 "[python]": {
     "editor.defaultFormatter": "charliermarsh.ruff",
     "editor.formatOnSave": true
-},
-"ruff.format.args": ["--config", "line-length=100"]
+}
 ```
 
 ## Getting help

docs/CONTRIBUTING.md

@@ -0,0 +1,165 @@
+## Contributing to Pipecat
+
+We welcome contributions of all kinds! Your help is appreciated. Follow these steps to get involved:
+
+1. **Fork this repository**: Start by forking the Pipecat Documentation repository to your GitHub account.
+
+2. **Clone the repository**: Clone your forked repository to your local machine.
+   ```bash
+   git clone https://github.com/your-username/pipecat
+   ```
+3. **Create a branch**: For your contribution, create a new branch.
+   ```bash
+   git checkout -b your-branch-name
+   ```
+4. **Make your changes**: Edit or add files as necessary.
+5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
+6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
+
+```bash
+git commit -m "Description of your changes"
+```
+
+7. **Push your changes**: Push your branch to your forked repository.
+
+```bash
+git push origin your-branch-name
+```
+
+9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo. 
+> Important: Describe the changes you've made clearly!
+
+Our maintainers will review your PR, and once everything is good, your contributions will be merged!
+
+
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official email address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at pipecat-ai@daily.co.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

docs/ISSUE_TEMPLATE.md

@@ -0,0 +1,22 @@
+# Description
+Is this reporting a bug or feature request?
+
+
+If reporting a bug, please fill out the following:
+
+### Environment
+- pipecat-ai version:
+- python version:
+- OS:
+
+### Issue description
+Provide a clear description of the issue.
+
+### Repro steps
+List the steps to reproduce the issue.
+
+### Expected behavior
+
+### Actual behavior
+
+### Logs

docs/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1 @@
+#### Please describe the changes in your PR. If it is addressing an issue, please reference that as well.

dot-env.template

@@ -46,5 +46,10 @@ PLAY_HT_API_KEY=...
 # OpenAI
 OPENAI_API_KEY=...
 
-#OpenPipe
+# OpenPipe
 OPENPIPE_API_KEY=...
+
+# Tavus
+TAVUS_API_KEY=...
+TAVUS_REPLICA_ID=...
+TAVUS_PERSONA_ID=...

examples/canonical-metrics/Dockerfile

@@ -1,16 +1,10 @@
 FROM python:3.10-bullseye
-
 RUN mkdir /app
-RUN mkdir /app/assets
-RUN mkdir /app/utils
 COPY *.py /app/
 COPY requirements.txt /app/
-copy assets/* /app/assets/
-copy utils/* /app/utils/
-
 WORKDIR /app
 RUN pip3 install -r requirements.txt
 
 EXPOSE 7860
 
-CMD ["python3", "server.py"]
+CMD ["python3", "server.py"]

examples/canonical-metrics/README.md

@@ -1,12 +1,41 @@
-# Simple Chatbot
+# Chatbot with canonical-metrics
 
-<img src="image.png" width="420px">
+This project implements a chatbot using a pipeline architecture that integrates audio processing, transcription, and a language model for conversational interactions. The chatbot operates within a daily communication environment, utilizing various services for text-to-speech and language model responses.
 
-This app connects you to a chatbot powered by GPT-4, complete with animations generated by Stable Video Diffusion.
+## Features
 
-See a video of it in action: https://x.com/kwindla/status/1778628911817183509
+- **Audio Input and Output**: Captures microphone input and plays back audio responses.
+- **Voice Activity Detection**: Utilizes Silero VAD to manage audio input intelligently.
+- **Text-to-Speech**: Integrates ElevenLabs TTS service to convert text responses into audio.
+- **Language Model Interaction**: Uses OpenAI's GPT-4 model to generate responses based on user input.
+- **Transcription Services**: Captures and transcribes participant speech for analytics.
+- **Metrics Collection**: Sends audio data for analysis via Canonical Metrics Service.
+
+## Requirements
+
+- Python 3.10+
+- `python-dotenv`
+- Additional libraries from the `pipecat` package.
+
+## Setup
+
+1. Clone the repository.
+2. Install the required packages.
+3. Set up environment variables for API keys:
+   - `OPENAI_API_KEY`
+   - `ELEVENLABS_API_KEY`
+   - `CANONICAL_API_KEY`
+   - `CANONICAL_API_URL`
+4. Run the script.
+
+## Usage
+
+The chatbot introduces itself and engages in conversations, providing brief and creative responses. Designed for flexibility, it can support multiple languages with appropriate configuration.
+
+## Events
+
+- Participants joining or leaving the call are handled dynamically, adjusting the chatbot's behavior accordingly.
 
-And a quick video walkthrough of the code: https://www.loom.com/share/13df1967161f4d24ade054e7f8753416
 
 ℹ️ The first time, things might take extra time to get started since VAD (Voice Activity Detection) model needs to be downloaded.
 
@@ -27,7 +56,7 @@ cp env.example .env # and add your credentials
 python server.py
 ```
 
-Then, visit `http://localhost:7860/start` in your browser to start a chatbot session.
+Then, visit `http://localhost:7860/` in your browser to start a chatbot session.
 
 ## Build and test the Docker image
 

examples/canonical-metrics/bot.py

@@ -14,20 +14,17 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
 from pipecat.services.canonical import CanonicalMetricsService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -92,8 +89,8 @@ async def main():
             },
         ]
 
-        user_response = LLMUserResponseAggregator()
-        assistant_response = LLMAssistantResponseAggregator()
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         """
         CanonicalMetrics uses AudioBufferProcessor under the hood to buffer the audio. On
@@ -113,13 +110,13 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # microphone
-                user_response,
+                context_aggregator.user(),
                 llm,
                 tts,
                 transport.output(),
                 audio_buffer_processor,  # captures audio into a buffer
                 canonical,  # uploads audio buffer to Canonical AI for metrics
-                assistant_response,
+                context_aggregator.assistant(),
             ]
         )
 
@@ -127,7 +124,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             await task.queue_frames([LLMMessagesFrame(messages)])
 
         @transport.event_handler("on_participant_left")

examples/canonical-metrics/env.example

@@ -2,4 +2,5 @@ DAILY_SAMPLE_ROOM_URL=https://yourdomain.daily.co/yourroom # (for joining the bo
 DAILY_API_KEY=7df...
 OPENAI_API_KEY=sk-PL...
 ELEVENLABS_API_KEY=aeb...
-CANONICAL_API_KEY=can...
+CANONICAL_API_KEY=can...
+CANONICAL_API_URL=

examples/canonical-metrics/server.py

@@ -59,7 +59,7 @@ app.add_middleware(
 )
 
 
-@app.get("/start")
+@app.get("/")
 async def start_agent(request: Request):
     print(f"!!! Creating room")
     room = await daily_helpers["rest"].create_room(DailyRoomParams())

examples/chatbot-audio-recording/README.md

@@ -27,7 +27,7 @@ cp env.example .env # and add your credentials
 python server.py
 ```
 
-Then, visit `http://localhost:7860/start` in your browser to start a chatbot session.
+Then, visit `http://localhost:7860/` in your browser to start a chatbot session.
 
 ## Build and test the Docker image
 

examples/chatbot-audio-recording/bot.py

@@ -9,23 +9,22 @@ import os
 import sys
 
 import aiohttp
+import datetime
+import wave
 from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.audio.audio_buffer_processor import AudioBufferProcessor
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -33,6 +32,20 @@ logger.remove(0)
 logger.add(sys.stderr, level="DEBUG")
 
 
+async def save_audio(audiobuffer):
+    if audiobuffer.has_audio():
+        merged_audio = audiobuffer.merge_audio_buffers()
+        filename = f"conversation_recording{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.wav"
+        with wave.open(filename, "wb") as wf:
+            wf.setnchannels(2)
+            wf.setsampwidth(2)
+            wf.setframerate(audiobuffer._sample_rate)
+            wf.writeframes(merged_audio)
+        print(f"Merged audio saved to {filename}")
+    else:
+        print("No audio data to save")
+
+
 async def main():
     async with aiohttp.ClientSession() as session:
         (room_url, token) = await configure(session)
@@ -90,19 +103,19 @@ async def main():
             },
         ]
 
-        user_response = LLMUserResponseAggregator()
-        assistant_response = LLMAssistantResponseAggregator()
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         audiobuffer = AudioBufferProcessor()
         pipeline = Pipeline(
             [
                 transport.input(),  # microphone
-                user_response,
+                context_aggregator.user(),
                 llm,
                 tts,
                 transport.output(),
                 audiobuffer,  # used to buffer the audio in the pipeline
-                assistant_response,
+                context_aggregator.assistant(),
             ]
         )
 
@@ -110,18 +123,14 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             await task.queue_frames([LLMMessagesFrame(messages)])
 
         @transport.event_handler("on_participant_left")
         async def on_participant_left(transport, participant, reason):
             print(f"Participant left: {participant}")
             await task.queue_frame(EndFrame())
-
-        @transport.event_handler("on_call_state_updated")
-        async def on_call_state_updated(transport, state):
-            if state == "left":
-                await task.queue_frame(EndFrame())
+            await save_audio(audiobuffer)
 
         runner = PipelineRunner()
 

examples/chatbot-audio-recording/server.py

@@ -59,7 +59,7 @@ app.add_middleware(
 )
 
 
-@app.get("/start")
+@app.get("/")
 async def start_agent(request: Request):
     print(f"!!! Creating room")
     room = await daily_helpers["rest"].create_room(DailyRoomParams())

examples/deployment/flyio-example/README.md

@@ -34,6 +34,6 @@ Note: you can do this manually via the fly.io dashboard under the "secrets" sub-
 
 Send a post request to your running fly.io instance:
 
-`curl --location --request POST 'https://YOUR_FLY_APP_NAME/start_bot'`
+`curl --location --request POST 'https://YOUR_FLY_APP_NAME/'`
 
 This request will wait until the machine enters into a `starting` state, before returning the a room URL and token to join.

examples/deployment/flyio-example/bot.py

@@ -3,18 +3,15 @@ import os
 import sys
 import argparse
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
 from pipecat.frames.frames import LLMMessagesFrame, EndFrame
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai import OpenAILLMService
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from loguru import logger
 
@@ -60,17 +57,17 @@ async def main(room_url: str, token: str):
         },
     ]
 
-    tma_in = LLMUserResponseAggregator(messages)
-    tma_out = LLMAssistantResponseAggregator(messages)
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
 
     pipeline = Pipeline(
         [
             transport.input(),
-            tma_in,
+            context_aggregator.user(),
             llm,
             tts,
             transport.output(),
-            tma_out,
+            context_aggregator.assistant(),
         ]
     )
 
@@ -78,7 +75,7 @@ async def main(room_url: str, token: str):
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
-        transport.capture_participant_transcription(participant["id"])
+        await transport.capture_participant_transcription(participant["id"])
         await task.queue_frames([LLMMessagesFrame(messages)])
 
     @transport.event_handler("on_participant_left")

examples/deployment/flyio-example/bot_runner.py

@@ -124,7 +124,7 @@ async def spawn_fly_machine(room_url: str, token: str):
     print(f"Machine joined room: {room_url}")
 
 
-@app.post("/start_bot")
+@app.post("/")
 async def start_bot(request: Request) -> JSONResponse:
     try:
         data = await request.json()

examples/dialin-chatbot/bot_daily.py

@@ -3,18 +3,16 @@ import os
 import sys
 import argparse
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
 from pipecat.frames.frames import LLMMessagesFrame, EndFrame
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport, DailyDialinSettings
-from pipecat.vad.silero import SileroVADAnalyzer
+
 from loguru import logger
 
 from dotenv import load_dotenv
@@ -65,17 +63,17 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
         },
     ]
 
-    tma_in = LLMUserResponseAggregator(messages)
-    tma_out = LLMAssistantResponseAggregator(messages)
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
 
     pipeline = Pipeline(
         [
             transport.input(),
-            tma_in,
+            context_aggregator.user(),
             llm,
             tts,
             transport.output(),
-            tma_out,
+            context_aggregator.assistant(),
         ]
     )
 
@@ -83,7 +81,7 @@ async def main(room_url: str, token: str, callId: str, callDomain: str):
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
-        transport.capture_participant_transcription(participant["id"])
+        await transport.capture_participant_transcription(participant["id"])
         await task.queue_frames([LLMMessagesFrame(messages)])
 
     @transport.event_handler("on_participant_left")

examples/dialin-chatbot/bot_runner.py

@@ -108,11 +108,9 @@ async def _create_daily_room(room_url, callId, callDomain=None, vendor="daily"):
     # Spawn a new agent, and join the user session
     # Note: this is mostly for demonstration purposes (refer to 'deployment' in docs)
     if vendor == "daily":
-        bot_proc = f"python3 - m bot_daily - u {room.url} - t {token} - i {
-            callId} - d {callDomain}"
+        bot_proc = f"python3 -m bot_daily -u {room.url} -t {token} -i {callId} -d {callDomain}"
     else:
-        bot_proc = f"python3 - m bot_twilio - u {room.url} - t {
-            token} - i {callId} - s {room.config.sip_endpoint}"
+        bot_proc = f"python3 -m bot_twilio -u {room.url} -t {token} -i {callId} -s {room.config.sip_endpoint}"
 
     try:
         subprocess.Popen(

examples/dialin-chatbot/bot_twilio.py

@@ -3,18 +3,15 @@ import os
 import sys
 import argparse
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
 from pipecat.frames.frames import LLMMessagesFrame, EndFrame
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from twilio.rest import Client
 
@@ -69,17 +66,17 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
         },
     ]
 
-    tma_in = LLMUserResponseAggregator(messages)
-    tma_out = LLMAssistantResponseAggregator(messages)
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
 
     pipeline = Pipeline(
         [
             transport.input(),
-            tma_in,
+            context_aggregator.user(),
             llm,
             tts,
             transport.output(),
-            tma_out,
+            context_aggregator.assistant(),
         ]
     )
 
@@ -87,7 +84,7 @@ async def main(room_url: str, token: str, callId: str, sipUri: str):
 
     @transport.event_handler("on_first_participant_joined")
     async def on_first_participant_joined(transport, participant):
-        transport.capture_participant_transcription(participant["id"])
+        await transport.capture_participant_transcription(participant["id"])
         await task.queue_frames([LLMMessagesFrame(messages)])
 
     @transport.event_handler("on_participant_left")

examples/foundational/01-say-one-thing.py

@@ -47,10 +47,15 @@ async def main():
 
         # Register an event handler so we can play the audio when the
         # participant joins.
-        @transport.event_handler("on_participant_joined")
-        async def on_new_participant_joined(transport, participant):
-            participant_name = participant["info"]["userName"] or ""
-            await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            participant_name = participant.get("info", {}).get("userName", "")
+            await task.queue_frame(TextFrame(f"Hello there, {participant_name}!"))
+
+        # Register an event handler to exit the application when the user leaves.
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         await runner.run(task)
 

examples/foundational/01b-livekit-audio.py

@@ -4,9 +4,6 @@ import os
 import sys
 
 import aiohttp
-from dotenv import load_dotenv
-from livekit import api  # pip install livekit-api
-from loguru import logger
 
 from pipecat.frames.frames import TextFrame
 from pipecat.pipeline.pipeline import Pipeline
@@ -15,6 +12,12 @@ from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.livekit import LiveKitParams, LiveKitTransport
 
+from livekit import api
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -78,7 +81,7 @@ async def main():
             url=url,
             token=token,
             room_name=room_name,
-            params=LiveKitParams(audio_out_enabled=True, audio_out_sample_rate=16000),
+            params=LiveKitParams(audio_out_enabled=True),
         )
 
         tts = CartesiaTTSService(

examples/foundational/02-llm-say-one-thing.py

@@ -57,7 +57,11 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            await task.queue_frames([LLMMessagesFrame(messages), EndFrame()])
+            await task.queue_frame(LLMMessagesFrame(messages))
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         await runner.run(task)
 

examples/foundational/03-still-frame.py

@@ -9,7 +9,7 @@ import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import TextFrame
+from pipecat.frames.frames import EndFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -51,11 +51,11 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            # Note that we do not put an EndFrame() item in the pipeline for this demo.
-            # This means that the bot will stay in the channel until it times out.
-            # An EndFrame() in the pipeline would cause the transport to shut
-            # down.
-            await task.queue_frames([TextFrame("a cat in the style of picasso")])
+            await task.queue_frame(TextFrame("a cat in the style of picasso"))
+
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
 
         await runner.run(task)
 

examples/foundational/06-listen-and-respond.py

@@ -5,35 +5,30 @@
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, LLMMessagesFrame, MetricsFrame
 from pipecat.metrics.metrics import (
-    TTFBMetricsData,
-    ProcessingMetricsData,
     LLMUsageMetricsData,
+    ProcessingMetricsData,
+    TTFBMetricsData,
     TTSUsageMetricsData,
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
 
 load_dotenv(override=True)
 
@@ -92,26 +87,30 @@ async def main():
                 "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
             },
         ]
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),
-                tma_in,
+                context_aggregator.user(),
                 llm,
                 tts,
                 ml,
                 transport.output(),
-                tma_out,
+                context_aggregator.assistant(),
             ]
         )
 
-        task = PipelineTask(pipeline)
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(enable_metrics=True, enable_usage_metrics=True),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/06a-image-sync.py

@@ -11,19 +11,16 @@ import sys
 
 from PIL import Image
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, OutputImageRawFrame, SystemFrame, TextFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaHttpTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from pipecat.transports.services.daily import DailyParams
 from runner import configure
@@ -105,8 +102,8 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         image_sync_aggregator = ImageSyncAggregator(
             os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
@@ -117,11 +114,11 @@ async def main():
             [
                 transport.input(),
                 image_sync_aggregator,
-                tma_in,
+                context_aggregator.user(),
                 llm,
                 tts,
                 transport.output(),
-                tma_out,
+                context_aggregator.assistant(),
             ]
         )
 
@@ -129,8 +126,8 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            participant_name = participant["info"]["userName"] or ""
-            transport.capture_participant_transcription(participant["id"])
+            participant_name = participant.get("info", {}).get("userName", "")
+            await transport.capture_participant_transcription(participant["id"])
             await task.queue_frames([TextFrame(f"Hi there {participant_name}!")])
 
         runner = PipelineRunner()

examples/foundational/07-interruptible-vad.py

@@ -0,0 +1,103 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.audio.vad.silero import SileroVAD
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_in_enabled=True,
+                audio_out_enabled=True,
+                transcription_enabled=True,
+            ),
+        )
+
+        vad = SileroVAD()
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                vad,
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/07-interruptible.py

@@ -9,18 +9,15 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -64,17 +61,17 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -90,7 +87,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07a-interruptible-anthropic.py

@@ -13,6 +13,7 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -21,7 +22,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.anthropic import AnthropicLLMService
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -82,7 +82,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([LLMMessagesFrame(messages)])
 

examples/foundational/07b-interruptible-langchain.py

@@ -10,6 +10,7 @@ import sys
 
 import aiohttp
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -21,7 +22,6 @@ from pipecat.processors.aggregators.llm_response import (
 from pipecat.processors.frameworks.langchain import LangchainProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain_community.chat_message_histories import ChatMessageHistory
@@ -109,7 +109,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             lc.set_participant_id(participant["id"])
             # Kick off the conversation.
             # the `LLMMessagesFrame` will be picked up by the LangchainProcessor using

examples/foundational/07c-interruptible-deepgram.py

@@ -13,18 +13,15 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -61,18 +58,18 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -80,7 +77,6 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07d-interruptible-elevenlabs.py

@@ -11,20 +11,17 @@ import sys
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -62,17 +59,17 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -88,7 +85,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07e-interruptible-playht.py

@@ -13,18 +13,16 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai import OpenAILLMService
 from pipecat.services.playht import PlayHTTTSService
+from pipecat.transcriptions.language import Language
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -42,7 +40,6 @@ async def main():
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
-                audio_out_sample_rate=16000,
                 transcription_enabled=True,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
@@ -53,6 +50,7 @@ async def main():
             user_id=os.getenv("PLAYHT_USER_ID"),
             api_key=os.getenv("PLAYHT_API_KEY"),
             voice_url="s3://voice-cloning-zero-shot/801a663f-efd0-4254-98d0-5c175514c3e8/jennifer/manifest.json",
+            params=PlayHTTTSService.InputParams(language=Language.EN),
         )
 
         llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
@@ -64,25 +62,33 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
-        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07f-interruptible-azure.py

@@ -9,17 +9,14 @@ import asyncio
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.azure import AzureLLMService, AzureSTTService, AzureTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 
 from runner import configure
@@ -44,7 +41,6 @@ async def main():
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
-                audio_out_sample_rate=16000,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
                 vad_audio_passthrough=True,
@@ -74,18 +70,18 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -93,7 +89,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07g-interruptible-openai-tts.py

@@ -11,19 +11,16 @@ import sys
 import aiohttp
 from dotenv import load_dotenv
 from loguru import logger
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
 from pipecat.services.openai import OpenAILLMService, OpenAITTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -59,17 +56,17 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -77,7 +74,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07h-interruptible-openpipe.py

@@ -9,18 +9,15 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openpipe import OpenPipeLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -70,17 +67,18 @@ async def main():
                 "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
             },
         ]
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -88,7 +86,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07i-interruptible-xtts.py

@@ -9,19 +9,15 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
-from pipecat.services.deepgram import DeepgramSTTService, DeepgramTTSService
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai import OpenAILLMService
 from pipecat.services.xtts import XTTSService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -67,17 +63,17 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -85,7 +81,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07j-interruptible-gladia.py

@@ -5,29 +5,24 @@
 #
 
 import asyncio
-import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import LLMMessagesFrame
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.gladia import GladiaSTTService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
-
-from runner import configure
-
-from loguru import logger
-
-from dotenv import load_dotenv
 
 load_dotenv(override=True)
 
@@ -69,18 +64,18 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -88,11 +83,16 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])
 
+        # Register an event handler to exit the application when the user leaves.
+        @transport.event_handler("on_participant_left")
+        async def on_participant_left(transport, participant, reason):
+            await task.queue_frame(EndFrame())
+
         runner = PipelineRunner()
 
         await runner.run(task)

examples/foundational/07k-interruptible-lmnt.py

@@ -9,18 +9,15 @@ import asyncio
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.lmnt import LmntTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -62,17 +59,17 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),  # User respones
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -80,7 +77,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07l-interruptible-together.py

@@ -13,6 +13,7 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -21,7 +22,6 @@ from pipecat.services.ai_services import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.together import TogetherLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -52,7 +52,7 @@ async def main():
 
         llm = TogetherLLMService(
             api_key=os.getenv("TOGETHER_API_KEY"),
-            model=os.getenv("TOGETHER_MODEL"),
+            model="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
             params=TogetherLLMService.InputParams(
                 temperature=1.0,
                 top_p=0.9,
@@ -96,7 +96,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([LLMMessagesFrame(messages)])
 

examples/foundational/07m-interruptible-aws.py

@@ -13,19 +13,16 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.aws import AWSTTSService
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -43,7 +40,6 @@ async def main():
             "Respond bot",
             DailyParams(
                 audio_out_enabled=True,
-                audio_out_sample_rate=16000,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
                 vad_audio_passthrough=True,
@@ -69,18 +65,18 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -88,7 +84,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07n-interruptible-google.py

@@ -13,19 +13,16 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.google import GoogleTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -66,18 +63,18 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 stt,  # STT
-                tma_in,  # User responses
+                context_aggregator.user(),  # User respones
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -85,7 +82,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/07o-interruptible-assemblyai.py

@@ -0,0 +1,97 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.services.assemblyai import AssemblyAISTTService
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = AssemblyAISTTService(
+            api_key=os.getenv("ASSEMBLYAI_API_KEY"),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                context_aggregator.user(),  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(pipeline, PipelineParams(allow_interruptions=True))
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/09-mirror.py

@@ -63,6 +63,7 @@ async def main():
             "Test",
             DailyParams(
                 audio_in_enabled=True,
+                audio_in_sample_rate=24000,
                 audio_out_enabled=True,
                 camera_out_enabled=True,
                 camera_out_is_live=True,
@@ -73,7 +74,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_video(participant["id"])
+            await transport.capture_participant_video(participant["id"])
 
         pipeline = Pipeline([transport.input(), MirrorProcessor(), transport.output()])
 

examples/foundational/09a-local-mirror.py

@@ -65,7 +65,7 @@ async def main():
         tk_root.title("Local Mirror")
 
         daily_transport = DailyTransport(
-            room_url, token, "Test", DailyParams(audio_in_enabled=True)
+            room_url, token, "Test", DailyParams(audio_in_enabled=True, audio_in_sample_rate=24000)
         )
 
         tk_transport = TkLocalTransport(
@@ -81,7 +81,7 @@ async def main():
 
         @daily_transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_video(participant["id"])
+            await transport.capture_participant_video(participant["id"])
 
         pipeline = Pipeline([daily_transport.input(), MirrorProcessor(), tk_transport.output()])
 

examples/foundational/10-wake-phrase.py

@@ -9,18 +9,15 @@ import aiohttp
 import os
 import sys
 
-from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.filters.wake_check_filter import WakeCheckFilter
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -65,18 +62,19 @@ async def main():
         ]
 
         hey_robot_filter = WakeCheckFilter(["hey robot", "hey, robot"])
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
                 hey_robot_filter,  # Filter out speech not directed at the robot
-                tma_in,  # User responses
+                context_aggregator.user(),  # User responses
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),  # Assistant spoken responses
             ]
         )
 
@@ -84,7 +82,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             await tts.say("Hi! If you want to talk to me, just say 'Hey Robot'.")
 
         runner = PipelineRunner()

examples/foundational/11-sound-effects.py

@@ -10,6 +10,7 @@ import os
 import sys
 import wave
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     Frame,
     LLMFullResponseEndFrame,
@@ -19,16 +20,12 @@ from pipecat.frames.frames import (
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMUserResponseAggregator,
-    LLMAssistantResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.processors.logger import FrameLogger
 from pipecat.services.cartesia import CartesiaHttpTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -113,8 +110,8 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
         out_sound = OutboundSoundEffectWrapper()
         in_sound = InboundSoundEffectWrapper()
         fl = FrameLogger("LLM Out")
@@ -123,7 +120,7 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),
-                tma_in,
+                context_aggregator.user(),
                 in_sound,
                 fl2,
                 llm,
@@ -131,13 +128,13 @@ async def main():
                 tts,
                 out_sound,
                 transport.output(),
-                tma_out,
+                context_aggregator.assistant(),
             ]
         )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             await tts.say("Hi, I'm listening!")
             await transport.send_audio(sounds["ding1.wav"])
 

examples/foundational/12-describe-video.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,7 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.moondream import MoondreamService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -84,8 +84,8 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await tts.say("Hi there! Feel free to ask me what I see.")
-            transport.capture_participant_video(participant["id"], framerate=0)
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(participant["id"], framerate=0)
+            await transport.capture_participant_transcription(participant["id"])
             image_requester.set_participant_id(participant["id"])
 
         pipeline = Pipeline(

examples/foundational/12a-describe-video-gemini-flash.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,7 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.google import GoogleLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -86,8 +86,8 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await tts.say("Hi there! Feel free to ask me what I see.")
-            transport.capture_participant_video(participant["id"], framerate=0)
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(participant["id"], framerate=0)
+            await transport.capture_participant_transcription(participant["id"])
             image_requester.set_participant_id(participant["id"])
 
         pipeline = Pipeline(

examples/foundational/12b-describe-video-gpt-4o.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,7 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -83,8 +83,8 @@ async def main():
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await tts.say("Hi there! Feel free to ask me what I see.")
-            transport.capture_participant_video(participant["id"], framerate=0)
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(participant["id"], framerate=0)
+            await transport.capture_participant_transcription(participant["id"])
             image_requester.set_participant_id(participant["id"])
 
         pipeline = Pipeline(

examples/foundational/12c-describe-video-anthropic.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import Frame, TextFrame, UserImageRequestFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,7 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -78,16 +78,13 @@ async def main():
         tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
-            params=CartesiaTTSService.InputParams(
-                sample_rate=16000,
-            ),
         )
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             await tts.say("Hi there! Feel free to ask me what I see.")
-            transport.capture_participant_video(participant["id"], framerate=0)
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(participant["id"], framerate=0)
+            await transport.capture_participant_transcription(participant["id"])
             image_requester.set_participant_id(participant["id"])
 
         pipeline = Pipeline(

examples/foundational/13c-gladia-transcription.py

@@ -0,0 +1,63 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import Frame, TranscriptionFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.gladia import GladiaSTTService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptionLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True)
+        )
+
+        stt = GladiaSTTService(
+            api_key=os.getenv("GLADIA_API_KEY"),
+            # live_options=LiveOptions(language=Language.FR),
+        )
+
+        tl = TranscriptionLogger()
+
+        pipeline = Pipeline([transport.input(), stt, tl])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/13d-assemblyai-transcription.py

@@ -0,0 +1,62 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import os
+import sys
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.frames.frames import Frame, TranscriptionFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineTask
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.services.assemblyai import AssemblyAISTTService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+class TranscriptionLogger(FrameProcessor):
+    async def process_frame(self, frame: Frame, direction: FrameDirection):
+        await super().process_frame(frame, direction)
+
+        if isinstance(frame, TranscriptionFrame):
+            print(f"Transcription: {frame.text}")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url, None, "Transcription bot", DailyParams(audio_in_enabled=True)
+        )
+
+        stt = AssemblyAISTTService(
+            api_key=os.getenv("ASSEMBLYAI_API_KEY"),
+        )
+
+        tl = TranscriptionLogger()
+
+        pipeline = Pipeline([transport.input(), stt, tl])
+
+        task = PipelineTask(pipeline)
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/14-function-calling.py

@@ -9,13 +9,13 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from openai.types.chat import ChatCompletionToolParam
 
@@ -127,7 +127,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/14a-function-calling-anthropic.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -16,7 +17,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -105,7 +105,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/14b-function-calling-anthropic-video.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -16,7 +17,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -160,8 +160,8 @@ If you need to use a tool, simply use the tool. Do not tell the user the tool yo
         async def on_first_participant_joined(transport, participant):
             global video_participant_id
             video_participant_id = participant["id"]
-            transport.capture_participant_transcription(video_participant_id)
-            transport.capture_participant_video(video_participant_id, framerate=0)
+            await transport.capture_participant_transcription(video_participant_id)
+            await transport.capture_participant_video(video_participant_id, framerate=0)
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/14c-function-calling-together.py

@@ -9,6 +9,7 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
@@ -16,7 +17,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext
 from pipecat.services.together import TogetherLLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from openai.types.chat import ChatCompletionToolParam
 
@@ -123,7 +123,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             # await tts.say("Hi! Ask me about the weather in San Francisco.")
 

examples/foundational/14d-function-calling-video.py

@@ -9,13 +9,13 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from openai.types.chat import ChatCompletionToolParam
 
@@ -153,8 +153,8 @@ indicate you should use the get_image tool are:
         async def on_first_participant_joined(transport, participant):
             global video_participant_id
             video_participant_id = participant["id"]
-            transport.capture_participant_transcription(participant["id"])
-            transport.capture_participant_video(video_participant_id, framerate=0)
+            await transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(video_participant_id, framerate=0)
             # Kick off the conversation.
             await tts.say("Hi! Ask me about the weather in San Francisco.")
 

examples/foundational/14e-function-calling-gemini.py

@@ -0,0 +1,173 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.google import GoogleLLMService
+from pipecat.services.openai import OpenAILLMContext
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+video_participant_id = None
+
+
+async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
+    location = arguments["location"]
+    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
+
+
+async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
+    logger.debug(f"!!! IN get_image {video_participant_id}, {arguments}")
+    question = arguments["question"]
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = GoogleLLMService(model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY"))
+        llm.register_function("get_weather", get_weather)
+        llm.register_function("get_image", get_image)
+
+        tools = [
+            {
+                "function_declarations": [
+                    {
+                        "name": "get_weather",
+                        "description": "Get the current weather",
+                        "parameters": {
+                            "type": "object",
+                            "properties": {
+                                "location": {
+                                    "type": "string",
+                                    "description": "The city and state, e.g. San Francisco, CA",
+                                },
+                                "format": {
+                                    "type": "string",
+                                    "enum": ["celsius", "fahrenheit"],
+                                    "description": "The temperature unit to use. Infer this from the users location.",
+                                },
+                            },
+                            "required": ["location", "format"],
+                        },
+                    },
+                    {
+                        "name": "get_image",
+                        "description": "Get and image from the camera or video stream.",
+                        "parameters": {
+                            "type": "object",
+                            "properties": {
+                                "question": {
+                                    "type": "string",
+                                    "description": "The question to to use when running inference on the acquired image.",
+                                },
+                            },
+                            "required": ["question"],
+                        },
+                    },
+                ]
+            }
+        ]
+
+        system_prompt = """\
+You are a helpful assistant who converses with a user and answers questions. Respond concisely to general questions.
+
+Your response will be turned into speech so use only simple words and punctuation.
+
+You have access to two tools: get_weather and get_image.
+
+You can respond to questions about the weather using the get_weather tool.
+
+You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
+indicate you should use the get_image tool are:
+  - What do you see?
+  - What's in the video?
+  - Can you describe the video?
+  - Tell me about what you see.
+  - Tell me something interesting about what you see.
+  - What's happening in the video?
+"""
+        messages = [
+            {"role": "system", "content": system_prompt},
+            {"role": "user", "content": "Say hello."},
+        ]
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                context_aggregator.user(),
+                llm,
+                tts,
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            global video_participant_id
+            video_participant_id = participant["id"]
+            await transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(video_participant_id, framerate=0)
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/15-switch-voices.py

@@ -9,6 +9,7 @@ import asyncio
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
@@ -19,7 +20,6 @@ from pipecat.processors.filters.function_filter import FunctionFilter
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from openai.types.chat import ChatCompletionToolParam
 
@@ -141,7 +141,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append(
                 {

examples/foundational/15a-switch-languages.py

@@ -9,7 +9,8 @@ import aiohttp
 import os
 import sys
 
-from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMMessagesFrame, TTSUpdateSettingsFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -18,9 +19,7 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.filters.function_filter import FunctionFilter
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.services.whisper import Model, WhisperSTTService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from openai.types.chat import ChatCompletionToolParam
 
@@ -61,16 +60,14 @@ async def main():
             token,
             "Pipecat",
             DailyParams(
-                audio_in_enabled=True,
                 audio_out_enabled=True,
+                transcription_enabled=True,
                 vad_enabled=True,
                 vad_analyzer=SileroVADAnalyzer(),
                 vad_audio_passthrough=True,
             ),
         )
 
-        stt = WhisperSTTService(model=Model.LARGE)
-
         english_tts = CartesiaTTSService(
             api_key=os.getenv("CARTESIA_API_KEY"),
             voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
@@ -116,7 +113,6 @@ async def main():
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                stt,  # STT
                 context_aggregator.user(),  # User responses
                 llm,  # LLM
                 ParallelPipeline(  # TTS (bot will speak the chosen language)
@@ -132,7 +128,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append(
                 {

examples/foundational/16-gpu-container-local-bot.py

@@ -13,14 +13,12 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.deepgram import DeepgramTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import (
@@ -28,7 +26,6 @@ from pipecat.transports.services.daily import (
     DailyTransport,
     DailyTransportMessageFrame,
 )
-from pipecat.vad.silero import SileroVADAnalyzer
 
 load_dotenv(override=True)
 
@@ -75,17 +72,17 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),  # Transport user input
-                tma_in,  # User responses
+                context_aggregator.user(),
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),
             ]
         )
 
@@ -95,7 +92,7 @@ async def main():
         # bot can "hear" and respond to them.
         @transport.event_handler("on_participant_joined")
         async def on_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
 
         # When the first participant joins, the bot should introduce itself.
         @transport.event_handler("on_first_participant_joined")
@@ -123,7 +120,7 @@ async def main():
                         )
                     )
                     # And push to the pipeline for the Daily transport.output to send
-                    await tma_in.push_frame(
+                    await task.queue_frame(
                         DailyTransportMessageFrame(
                             message={"latency-pong-pipeline-delivery": {"ts": ts}},
                             participant_id=sender,

examples/foundational/17-detect-user-idle.py

@@ -9,19 +9,16 @@ import aiohttp
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.user_idle_processor import UserIdleProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -65,8 +62,8 @@ async def main():
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         async def user_idle_callback(user_idle: UserIdleProcessor):
             messages.append(
@@ -83,11 +80,11 @@ async def main():
             [
                 transport.input(),  # Transport user input
                 user_idle,  # Idle user check-in
-                tma_in,  # User responses
+                context_aggregator.user(),
                 llm,  # LLM
                 tts,  # TTS
                 transport.output(),  # Transport bot output
-                tma_out,  # Assistant spoken responses
+                context_aggregator.assistant(),
             ]
         )
 
@@ -102,7 +99,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             messages.append({"role": "system", "content": "Please introduce yourself to the user."})
             await task.queue_frames([LLMMessagesFrame(messages)])

examples/foundational/19-openai-realtime-beta.py

@@ -14,21 +14,19 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.openai_llm_context import (
-    OpenAILLMContext,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.openai_realtime_beta import (
     InputAudioTranscription,
-    OpenAILLMServiceRealtimeBeta,
+    OpenAIRealtimeBetaLLMService,
     SessionProperties,
     TurnDetection,
 )
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
-from pipecat.vad.vad_analyzer import VADParams
 
 load_dotenv(override=True)
 
@@ -116,7 +114,7 @@ unless specifically asked to elaborate on a topic.
 Remember, your responses should be short. Just one or two sentences, usually.""",
         )
 
-        llm = OpenAILLMServiceRealtimeBeta(
+        llm = OpenAIRealtimeBetaLLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             session_properties=session_properties,
             start_audio_paused=False,
@@ -126,7 +124,24 @@ Remember, your responses should be short. Just one or two sentences, usually."""
         # llm.register_function(None, fetch_weather_from_api)
         llm.register_function("get_current_weather", fetch_weather_from_api)
 
-        context = OpenAILLMContext([{"role": "user", "content": "Say hello!"}], tools)
+        # Create a standard OpenAI LLM context object using the normal messages format. The
+        # OpenAIRealtimeBetaLLMService will convert this internally to messages that the
+        # openai WebSocket API can understand.
+        context = OpenAILLMContext(
+            [{"role": "user", "content": "Say hello!"}],
+            # [{"role": "user", "content": [{"type": "text", "text": "Say hello!"}]}],
+            #     [
+            #         {
+            #             "role": "user",
+            #             "content": [
+            #                 {"type": "text", "text": "Say"},
+            #                 {"type": "text", "text": "yo what's up!"},
+            #             ],
+            #         }
+            #     ],
+            tools,
+        )
+
         context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
@@ -151,7 +166,7 @@ Remember, your responses should be short. Just one or two sentences, usually."""
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/20a-persistent-context-openai.py

@@ -16,6 +16,8 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -26,8 +28,6 @@ from pipecat.services.openai import OpenAILLMService
 from pipecat.services.cartesia import CartesiaTTSService
 
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
-from pipecat.vad.vad_analyzer import VADParams
 
 load_dotenv(override=True)
 
@@ -223,7 +223,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/20b-persistent-context-openai-realtime.py

@@ -16,6 +16,8 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -24,13 +26,11 @@ from pipecat.processors.aggregators.openai_llm_context import (
 )
 from pipecat.services.openai_realtime_beta import (
     InputAudioTranscription,
-    OpenAILLMServiceRealtimeBeta,
+    OpenAIRealtimeBetaLLMService,
     SessionProperties,
     TurnDetection,
 )
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
-from pipecat.vad.vad_analyzer import VADParams
 
 load_dotenv(override=True)
 
@@ -211,7 +211,7 @@ unless specifically asked to elaborate on a topic.
 Remember, your responses should be short. Just one or two sentences, usually.""",
         )
 
-        llm = OpenAILLMServiceRealtimeBeta(
+        llm = OpenAIRealtimeBetaLLMService(
             api_key=os.getenv("OPENAI_API_KEY"),
             session_properties=session_properties,
             start_audio_paused=False,
@@ -249,7 +249,7 @@ Remember, your responses should be short. Just one or two sentences, usually."""
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/20c-persistent-context-anthropic.py

@@ -16,6 +16,8 @@ from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -26,8 +28,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.anthropic import AnthropicLLMService
 
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
-from pipecat.vad.vad_analyzer import VADParams
 
 load_dotenv(override=True)
 
@@ -219,7 +219,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             # Kick off the conversation.
             await task.queue_frames([context_aggregator.user().get_context_frame()])
 

examples/foundational/20d-persistent-context-gemini.py

@@ -0,0 +1,290 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import glob
+import json
+import os
+import sys
+from datetime import datetime
+
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from runner import configure
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.audio.vad.vad_analyzer import VADParams
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.openai_llm_context import (
+    OpenAILLMContext,
+)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.google import GoogleLLMService
+
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+video_participant_id = None
+
+
+BASE_FILENAME = "/tmp/pipecat_conversation_"
+tts = None
+
+
+async def fetch_weather_from_api(function_name, tool_call_id, args, llm, context, result_callback):
+    temperature = 75 if args["format"] == "fahrenheit" else 24
+    await result_callback(
+        {
+            "conditions": "nice",
+            "temperature": temperature,
+            "format": args["format"],
+            "timestamp": datetime.now().strftime("%Y%m%d_%H%M%S"),
+        }
+    )
+
+
+async def get_image(function_name, tool_call_id, arguments, llm, context, result_callback):
+    question = arguments["question"]
+    await llm.request_image_frame(user_id=video_participant_id, text_content=question)
+
+
+async def get_saved_conversation_filenames(
+    function_name, tool_call_id, args, llm, context, result_callback
+):
+    # Construct the full pattern including the BASE_FILENAME
+    full_pattern = f"{BASE_FILENAME}*.json"
+
+    # Use glob to find all matching files
+    matching_files = glob.glob(full_pattern)
+    logger.debug(f"matching files: {matching_files}")
+
+    await result_callback({"filenames": matching_files})
+
+
+async def save_conversation(function_name, tool_call_id, args, llm, context, result_callback):
+    timestamp = datetime.now().strftime("%Y-%m-%d_%H:%M:%S")
+    filename = f"{BASE_FILENAME}{timestamp}.json"
+    logger.debug(
+        f"writing conversation to {filename}\n{json.dumps(context.get_messages_for_logging(), indent=4)}"
+    )
+    try:
+        with open(filename, "w") as file:
+            # todo: extract 'system' into the first message in the list
+            messages = context.get_messages_for_persistent_storage()
+            # remove the last message (the instruction to save the context)
+            messages.pop()
+            json.dump(messages, file, indent=2)
+        await result_callback({"success": True})
+    except Exception as e:
+        logger.debug(f"error saving conversation: {e}")
+        await result_callback({"success": False, "error": str(e)})
+
+
+async def load_conversation(function_name, tool_call_id, args, llm, context, result_callback):
+    global tts
+    filename = args["filename"]
+    logger.debug(f"loading conversation from {filename}")
+    try:
+        with open(filename, "r") as file:
+            context.set_messages(json.load(file))
+        await result_callback(
+            {
+                "success": True,
+                "message": "The most recent conversation has been loaded. Awaiting further instructions.",
+            }
+        )
+    except Exception as e:
+        await result_callback({"success": False, "error": str(e)})
+
+
+# Test message munging ...
+messages = [
+    {
+        "role": "system",
+        "content": """You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your
+capabilities in a succinct way. Your output will be converted to audio so don't include special
+characters in your answers. Respond to what the user said in a creative and helpful way.
+
+You have several tools you can use to help you.
+
+You can respond to questions about the weather using the get_weather tool.
+
+You can save the current conversation using the save_conversation tool. This tool allows you to save
+the current conversation to external storage. If the user asks you to save the conversation, use this
+save_conversation too.
+
+You can load a saved conversation using the load_conversation tool. This tool allows you to load a
+conversation from external storage. You can get a list of conversations that have been saved using the
+get_saved_conversation_filenames tool.
+
+You can answer questions about the user's video stream using the get_image tool. Some examples of phrases that \
+indicate you should use the get_image tool are:
+  - What do you see?
+  - What's in the video?
+  - Can you describe the video?
+  - Tell me about what you see.
+  - Tell me something interesting about what you see.
+  - What's happening in the video?
+        """,
+    },
+    # {"role": "user", "content": ""},
+    # {"role": "assistant", "content": []},
+    # {"role": "user", "content": "Tell me"},
+    # {"role": "user", "content": "a joke"},
+]
+tools = [
+    {
+        "function_declarations": [
+            {
+                "name": "get_current_weather",
+                "description": "Get the current weather",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "The city and state, e.g. San Francisco, CA",
+                        },
+                        "format": {
+                            "type": "string",
+                            "enum": ["celsius", "fahrenheit"],
+                            "description": "The temperature unit to use. Infer this from the users location.",
+                        },
+                    },
+                    "required": ["location", "format"],
+                },
+            },
+            {
+                "name": "save_conversation",
+                "description": "Save the current conversation. Use this function to persist the current conversation to external storage.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "user_request_text": {
+                            "type": "string",
+                            "description": "The text of the user's request to save the conversation.",
+                        }
+                    },
+                    "required": ["user_request_text"],
+                },
+            },
+            {
+                "name": "get_saved_conversation_filenames",
+                "description": "Get a list of saved conversation histories. Returns a list of filenames. Each filename includes a date and timestamp. Each file is conversation history that can be loaded into this session.",
+                "parameters": None,
+            },
+            {
+                "name": "load_conversation",
+                "description": "Load a conversation history. Use this function to load a conversation history into the current session.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "filename": {
+                            "type": "string",
+                            "description": "The filename of the conversation history to load.",
+                        }
+                    },
+                    "required": ["filename"],
+                },
+            },
+            {
+                "name": "get_image",
+                "description": "Get and image from the camera or video stream.",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "question": {
+                            "type": "string",
+                            "description": "The question to to use when running inference on the acquired image.",
+                        },
+                    },
+                    "required": ["question"],
+                },
+            },
+        ]
+    },
+]
+
+
+async def main():
+    global tts
+    async with aiohttp.ClientSession() as session:
+        (room_url, token) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            token,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                transcription_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.8)),
+            ),
+        )
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        llm = GoogleLLMService(model="gemini-1.5-flash-latest", api_key=os.getenv("GOOGLE_API_KEY"))
+
+        # you can either register a single function for all function calls, or specific functions
+        # llm.register_function(None, fetch_weather_from_api)
+        llm.register_function("get_current_weather", fetch_weather_from_api)
+        llm.register_function("save_conversation", save_conversation)
+        llm.register_function("get_saved_conversation_filenames", get_saved_conversation_filenames)
+        llm.register_function("load_conversation", load_conversation)
+        llm.register_function("get_image", get_image)
+
+        context = OpenAILLMContext(messages, tools)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                context_aggregator.user(),
+                llm,  # LLM
+                tts,
+                context_aggregator.assistant(),
+                transport.output(),  # Transport bot output
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                # report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            global video_participant_id
+            video_participant_id = participant["id"]
+            await transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(video_participant_id, framerate=0)
+            # Kick off the conversation.
+            await task.queue_frames([context_aggregator.user().get_context_frame()])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/21-tavus-layer.py

@@ -0,0 +1,133 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from typing import Any, Mapping
+
+from pipecat.frames.frames import LLMMessagesFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.llm_response import (
+    LLMAssistantResponseAggregator,
+    LLMUserResponseAggregator,
+)
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.tavus import TavusVideoService
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        tavus = TavusVideoService(
+            api_key=os.getenv("TAVUS_API_KEY"),
+            replica_id=os.getenv("TAVUS_REPLICA_ID"),
+            persona_id=os.getenv("TAVUS_PERSONA_ID", "pipecat0"),
+            session=session,
+        )
+
+        # get persona, look up persona_name, set this as the bot name to ignore
+        persona_name = await tavus.get_persona_name()
+        room_url = await tavus.initialize()
+
+        transport = DailyTransport(
+            room_url=room_url,
+            token=None,
+            bot_name="Pipecat bot",
+            params=DailyParams(
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab",
+        )
+
+        llm = OpenAILLMService(model="gpt-4o-mini")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        tma_in = LLMUserResponseAggregator(messages)
+        tma_out = LLMAssistantResponseAggregator(messages)
+
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,  # STT
+                tma_in,  # User responses
+                llm,  # LLM
+                tts,  # TTS
+                tavus,  # Tavus output layer
+                transport.output(),  # Transport bot output
+                tma_out,  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_participant_joined")
+        async def on_participant_joined(
+            transport: DailyTransport, participant: Mapping[str, Any]
+        ) -> None:
+            # Ignore the Tavus replica's microphone
+            if participant.get("info", {}).get("userName", "") == persona_name:
+                logger.debug(f"Ignoring {participant['id']}'s microphone")
+                await transport.update_subscriptions(
+                    participant_settings={
+                        participant["id"]: {
+                            "media": {"microphone": "unsubscribed"},
+                        }
+                    }
+                )
+
+            if participant.get("info", {}).get("userName", "") != persona_name:
+                # Kick off the conversation.
+                messages.append(
+                    {"role": "system", "content": "Please introduce yourself to the user."}
+                )
+                await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/22-natural-conversation.py

@@ -0,0 +1,168 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMMessagesFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.gated_openai_llm_context import GatedOpenAILLMContextAggregator
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
+from pipecat.processors.filters.null_filter import NullFilter
+from pipecat.processors.filters.wake_notifier_filter import WakeNotifierFilter
+from pipecat.processors.user_idle_processor import UserIdleProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.sync.event_notifier import EventNotifier
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        # This is the LLM that will be used to detect if the user has finished a
+        # statement. This doesn't really need to be an LLM, we could use NLP
+        # libraries for that, but it was easier as an example because we
+        # leverage the context aggregators.
+        statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        statement_messages = [
+            {
+                "role": "system",
+                "content": "Determine if the user's statement is a complete sentence or question, ending in a natural pause or punctuation. Return 'YES' if it is complete and 'NO' if it seems to leave a thought unfinished.",
+            },
+        ]
+
+        statement_context = OpenAILLMContext(statement_messages)
+        statement_context_aggregator = statement_llm.create_context_aggregator(statement_context)
+
+        # This is the regular LLM.
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        # We have instructed the LLM to return 'YES' if it thinks the user
+        # completed a sentence. So, if it's 'YES' we will return true in this
+        # predicate which will wake up the notifier.
+        async def wake_check_filter(frame):
+            return frame.text == "YES"
+
+        # This is a notifier that we use to synchronize the two LLMs.
+        notifier = EventNotifier()
+
+        # This a filter that will wake up the notifier if the given predicate
+        # (wake_check_filter) returns true.
+        completness_check = WakeNotifierFilter(
+            notifier, types=(TextFrame,), filter=wake_check_filter
+        )
+
+        # This processor keeps the last context and will let it through once the
+        # notifier is woken up.
+        gated_context_aggregator = GatedOpenAILLMContextAggregator(notifier)
+
+        # Notify if the user hasn't said anything.
+        async def user_idle_notifier(frame):
+            await notifier.notify()
+
+        # Sometimes the LLM will fail detecting if a user has completed a
+        # sentence, this will wake up the notifier if that happens.
+        user_idle = UserIdleProcessor(callback=user_idle_notifier, timeout=3.0)
+
+        # The ParallePipeline input are the user transcripts. We have two
+        # contexts. The first one will be used to determine if the user finished
+        # a statement and if so the notifier will be woken up. The second
+        # context is simply the regular context but it's gated waiting for the
+        # notifier to be woken up.
+        pipeline = Pipeline(
+            [
+                transport.input(),  # Transport user input
+                stt,
+                ParallelPipeline(
+                    [
+                        statement_context_aggregator.user(),
+                        statement_llm,
+                        completness_check,
+                        NullFilter(),
+                    ],
+                    [context_aggregator.user(), gated_context_aggregator, llm],
+                ),
+                user_idle,
+                tts,  # TTS
+                transport.output(),  # Transport bot output
+                context_aggregator.assistant(),  # Assistant spoken responses
+            ]
+        )
+
+        task = PipelineTask(
+            pipeline,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/foundational/22b-natural-conversation-anthropic.py

@@ -0,0 +1,212 @@
+#
+# Copyright (c) 2024, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+import asyncio
+import aiohttp
+import os
+import sys
+
+from pipecat.audio.vad.silero import SileroVADAnalyzer
+from pipecat.frames.frames import LLMMessagesFrame, TextFrame
+from pipecat.pipeline.pipeline import Pipeline
+from pipecat.pipeline.parallel_pipeline import ParallelPipeline
+from pipecat.pipeline.runner import PipelineRunner
+from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.processors.aggregators.gated_openai_llm_context import GatedOpenAILLMContextAggregator
+from pipecat.processors.aggregators.openai_llm_context import (
+    OpenAILLMContext,
+    OpenAILLMContextFrame,
+)
+from pipecat.processors.filters.null_filter import NullFilter
+from pipecat.processors.filters.wake_notifier_filter import WakeNotifierFilter
+from pipecat.processors.user_idle_processor import UserIdleProcessor
+from pipecat.services.cartesia import CartesiaTTSService
+from pipecat.services.deepgram import DeepgramSTTService
+from pipecat.services.openai import OpenAILLMService
+from pipecat.sync.event_notifier import EventNotifier
+from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
+from pipecat.frames.frames import Frame
+
+
+from runner import configure
+
+from loguru import logger
+
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
+logger.remove(0)
+logger.add(sys.stderr, level="DEBUG")
+
+
+async def main():
+    async with aiohttp.ClientSession() as session:
+        (room_url, _) = await configure(session)
+
+        transport = DailyTransport(
+            room_url,
+            None,
+            "Respond bot",
+            DailyParams(
+                audio_out_enabled=True,
+                vad_enabled=True,
+                vad_analyzer=SileroVADAnalyzer(),
+                vad_audio_passthrough=True,
+            ),
+        )
+
+        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+
+        tts = CartesiaTTSService(
+            api_key=os.getenv("CARTESIA_API_KEY"),
+            voice_id="79a125e8-cd45-4c13-8a67-188112f4dd22",  # British Lady
+        )
+
+        # This is the LLM that will be used to detect if the user has finished a
+        # statement. This doesn't really need to be an LLM, we could use NLP
+        # libraries for that, but it was easier as an example because we
+        # leverage the context aggregators.
+        statement_llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        statement_messages = [
+            {
+                "role": "system",
+                "content": "Determine if the user's statement is a complete sentence or question, ending in a natural pause or punctuation. Return 'YES' if it is complete and 'NO' if it seems to leave a thought unfinished.",
+            },
+        ]
+
+        statement_context = OpenAILLMContext(statement_messages)
+        statement_context_aggregator = statement_llm.create_context_aggregator(statement_context)
+
+        # This is the regular LLM.
+        llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"), model="gpt-4o")
+
+        messages = [
+            {
+                "role": "system",
+                "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
+            },
+        ]
+
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
+
+        # We have instructed the LLM to return 'YES' if it thinks the user
+        # completed a sentence. So, if it's 'YES' we will return true in this
+        # predicate which will wake up the notifier.
+        async def wake_check_filter(frame):
+            logger.debug(f"Completeness check frame: {frame}")
+            return frame.text == "YES"
+
+        # This is a notifier that we use to synchronize the two LLMs.
+        notifier = EventNotifier()
+
+        # This a filter that will wake up the notifier if the given predicate
+        # (wake_check_filter) returns true.
+        completeness_check = WakeNotifierFilter(
+            notifier, types=(TextFrame,), filter=wake_check_filter
+        )
+
+        # This processor keeps the last context and will let it through once the
+        # notifier is woken up.
+        gated_context_aggregator = GatedOpenAILLMContextAggregator(notifier)
+
+        # Notify if the user hasn't said anything.
+        async def user_idle_notifier(frame):
+            await notifier.notify()
+
+        # Sometimes the LLM will fail detecting if a user has completed a
+        # sentence, this will wake up the notifier if that happens.
+        user_idle = UserIdleProcessor(callback=user_idle_notifier, timeout=3.0)
+
+        class StatementJudgeContextFilter(FrameProcessor):
+            async def process_frame(self, frame: Frame, direction: FrameDirection):
+                await super().process_frame(frame, direction)
+                if isinstance(frame, OpenAILLMContextFrame):
+                    logger.debug(f"Context Frame: {frame}")
+                    await self.push_frame(frame, direction)
+
+        class GatedTTSOutput(FrameProcessor):
+            async def process_frame(self, frame: Frame, direction: FrameDirection):
+                await super().process_frame(frame, direction)
+                await self.push_frame(frame, direction)
+
+        # The ParallePipeline input are the user transcripts. We have two
+        # contexts. The first one will be used to determine if the user finished
+        # a statement and if so the notifier will be woken up. The second
+        # context is simply the regular context but it's gated waiting for the
+        # notifier to be woken up.
+        pipeline = Pipeline(
+            [
+                transport.input(),
+                stt,
+                ParallelPipeline(
+                    [
+                        statement_context_aggregator.user(),
+                        statement_llm,
+                        completeness_check,
+                        NullFilter(),
+                    ],
+                    [context_aggregator.user(), gated_context_aggregator, llm],
+                ),
+                user_idle,
+                tts,  # TTS
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        pipeline_x = Pipeline(
+            [
+                transport.input(),
+                stt,
+                user_idle,
+                context_aggregator.user(),
+                ParallelPipeline(
+                    [
+                        StatementJudgeContextFilter(),
+                        statement_llm,
+                        completeness_check,
+                        NullFilter(),
+                    ],
+                    [
+                        llm,
+                        tts,
+                        GatedTTSOutput(),
+                    ],
+                ),
+                transport.output(),
+                context_aggregator.assistant(),
+            ]
+        )
+
+        task = PipelineTask(
+            # pipeline,
+            pipeline_x,
+            PipelineParams(
+                allow_interruptions=True,
+                enable_metrics=True,
+                enable_usage_metrics=True,
+                report_only_initial_ttfb=True,
+            ),
+        )
+
+        @transport.event_handler("on_first_participant_joined")
+        async def on_first_participant_joined(transport, participant):
+            await transport.capture_participant_transcription(participant["id"])
+            # Kick off the conversation.
+            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
+            await task.queue_frames([LLMMessagesFrame(messages)])
+
+        runner = PipelineRunner()
+
+        await runner.run(task)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

examples/moondream-chatbot/README.md

@@ -24,7 +24,7 @@ cp env.example .env # and add your credentials
 python server.py
 ```
 
-Then, visit `http://localhost:7860/start` in your browser to start a chatbot
+Then, visit `http://localhost:7860/` in your browser to start a chatbot
 session.
 
 ## Build and test the Docker image
@@ -41,4 +41,4 @@ docker build -t moonbot -f Dockerfile.intel .
 docker run --env-file .env -p 7860:7860 --device /dev/dri moonbot
 ```
 
-You can try to visit `http://localhost:7860/start` again.
+You can try to visit `http://localhost:7860/` again.

examples/moondream-chatbot/bot.py

@@ -11,6 +11,7 @@ import sys
 
 from PIL import Image
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import (
     ImageRawFrame,
     OutputImageRawFrame,
@@ -23,12 +24,11 @@ from pipecat.frames.frames import (
     UserImageRawFrame,
     UserImageRequestFrame,
 )
-
 from pipecat.pipeline.parallel_pipeline import ParallelPipeline
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_response import LLMUserResponseAggregator
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.aggregators.sentence import SentenceAggregator
 from pipecat.processors.aggregators.vision_image_frame import VisionImageFrameAggregator
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
@@ -36,7 +36,6 @@ from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.moondream import MoondreamService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -183,17 +182,19 @@ async def main():
             },
         ]
 
-        ura = LLMUserResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),
-                ura,
+                context_aggregator.user(),
                 llm,
                 ParallelPipeline([sa, ir, va, moondream], [tf, imgf]),
                 tts,
                 ta,
                 transport.output(),
+                context_aggregator.assistant(),
             ]
         )
 
@@ -202,8 +203,8 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
-            transport.capture_participant_video(participant["id"], framerate=0)
+            await transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_video(participant["id"], framerate=0)
             ir.set_participant_id(participant["id"])
             await task.queue_frames([LLMMessagesFrame(messages)])
 

examples/moondream-chatbot/server.py

@@ -57,7 +57,7 @@ app.add_middleware(
 )
 
 
-@app.get("/start")
+@app.get("/")
 async def start_agent(request: Request):
     print(f"!!! Creating room")
     room = await daily_helpers["rest"].create_room(DailyRoomParams())

examples/patient-intake/README.md

@@ -54,7 +54,7 @@ cp env.example .env # and add your credentials
 python server.py
 ```
 
-Then, visit `http://localhost:7860/start` in your browser to start a chatbot session.
+Then, visit `http://localhost:7860/` in your browser to start a chatbot session.
 
 ## Build and test the Docker image
 

examples/patient-intake/bot.py

@@ -10,6 +10,7 @@ import os
 import sys
 import wave
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import OutputAudioRawFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
@@ -19,7 +20,6 @@ from pipecat.processors.frame_processor import FrameDirection
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMContext, OpenAILLMContextFrame, OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -352,7 +352,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             print(f"Context is: {context}")
             await task.queue_frames([OpenAILLMContextFrame(context)])
 

examples/patient-intake/server.py

@@ -57,7 +57,7 @@ app.add_middleware(
 )
 
 
-@app.get("/start")
+@app.get("/")
 async def start_agent(request: Request):
     print(f"!!! Creating room")
     room = await daily_helpers["rest"].create_room(DailyRoomParams())
@@ -128,7 +128,7 @@ if __name__ == "__main__":
     parser.add_argument("--reload", action="store_true", help="Reload code on change")
 
     config = parser.parse_args()
-    print(f"to join a test room, visit http://localhost:{config.port}/start")
+    print(f"to join a test room, visit http://localhost:{config.port}/")
     uvicorn.run(
         "server:app",
         host=config.host,

examples/simple-chatbot/README.md

@@ -27,7 +27,7 @@ cp env.example .env # and add your credentials
 python server.py
 ```
 
-Then, visit `http://localhost:7860/start` in your browser to start a chatbot session.
+Then, visit `http://localhost:7860/` in your browser to start a chatbot session.
 
 ## Build and test the Docker image
 

examples/simple-chatbot/bot.py

@@ -11,13 +11,10 @@ import sys
 
 from PIL import Image
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
 from pipecat.frames.frames import (
     OutputImageRawFrame,
     SpriteFrame,
@@ -26,11 +23,11 @@ from pipecat.frames.frames import (
     TTSAudioRawFrame,
     TTSStoppedFrame,
 )
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -143,20 +140,20 @@ async def main():
             },
         ]
 
-        user_response = LLMUserResponseAggregator()
-        assistant_response = LLMAssistantResponseAggregator()
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         ta = TalkingAnimation()
 
         pipeline = Pipeline(
             [
                 transport.input(),
-                user_response,
+                context_aggregator.user(),
                 llm,
                 tts,
                 ta,
                 transport.output(),
-                assistant_response,
+                context_aggregator.assistant(),
             ]
         )
 

examples/simple-chatbot/server.py

@@ -17,6 +17,10 @@ from fastapi.responses import JSONResponse, RedirectResponse
 
 from pipecat.transports.services.helpers.daily_rest import DailyRESTHelper, DailyRoomParams
 
+from dotenv import load_dotenv
+
+load_dotenv(override=True)
+
 MAX_BOTS_PER_ROOM = 1
 
 # Bot sub-process dict for status reporting and concurrency control
@@ -57,7 +61,7 @@ app.add_middleware(
 )
 
 
-@app.get("/start")
+@app.get("/")
 async def start_agent(request: Request):
     print(f"!!! Creating room")
     room = await daily_helpers["rest"].create_room(DailyRoomParams())

examples/storytelling-chatbot/frontend/components/App.tsx

@@ -27,7 +27,7 @@ export default function Call() {
 
     // Create a new room for the story session
     try {
-      const response = await fetch("/start_bot", {
+      const response = await fetch("/", {
         method: "POST",
         headers: {
           "Content-Type": "application/json",

examples/storytelling-chatbot/frontend/package-lock.json

@@ -299,9 +299,9 @@
       }
     },
     "node_modules/@next/env": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.14.tgz",
-      "integrity": "sha512-/0hWQfiaD5//LvGNgc8PjvyqV50vGK0cADYzaoOOGN8fxzBn3iAiaq3S0tCRnFBldq0LVveLcxCTi41ZoYgAgg=="
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/env/-/env-14.2.15.tgz",
+      "integrity": "sha512-S1qaj25Wru2dUpcIZMjxeMVSwkt8BK4dmWHHiBuRstcIyOsMapqT4A4jSB6onvqeygkSSmOkyny9VVx8JIGamQ=="
     },
     "node_modules/@next/eslint-plugin-next": {
       "version": "14.1.4",
@@ -313,9 +313,9 @@
       }
     },
     "node_modules/@next/swc-darwin-arm64": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.14.tgz",
-      "integrity": "sha512-bsxbSAUodM1cjYeA4o6y7sp9wslvwjSkWw57t8DtC8Zig8aG8V6r+Yc05/9mDzLKcybb6EN85k1rJDnMKBd9Gw==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-arm64/-/swc-darwin-arm64-14.2.15.tgz",
+      "integrity": "sha512-Rvh7KU9hOUBnZ9TJ28n2Oa7dD9cvDBKua9IKx7cfQQ0GoYUwg9ig31O2oMwH3wm+pE3IkAQ67ZobPfEgurPZIA==",
       "cpu": [
         "arm64"
       ],
@@ -328,9 +328,9 @@
       }
     },
     "node_modules/@next/swc-darwin-x64": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.14.tgz",
-      "integrity": "sha512-cC9/I+0+SK5L1k9J8CInahduTVWGMXhQoXFeNvF0uNs3Bt1Ub0Azb8JzTU9vNCr0hnaMqiWu/Z0S1hfKc3+dww==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-darwin-x64/-/swc-darwin-x64-14.2.15.tgz",
+      "integrity": "sha512-5TGyjFcf8ampZP3e+FyCax5zFVHi+Oe7sZyaKOngsqyaNEpOgkKB3sqmymkZfowy3ufGA/tUgDPPxpQx931lHg==",
       "cpu": [
         "x64"
       ],
@@ -343,9 +343,9 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-gnu": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.14.tgz",
-      "integrity": "sha512-RMLOdA2NU4O7w1PQ3Z9ft3PxD6Htl4uB2TJpocm+4jcllHySPkFaUIFacQ3Jekcg6w+LBaFvjSPthZHiPmiAUg==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-gnu/-/swc-linux-arm64-gnu-14.2.15.tgz",
+      "integrity": "sha512-3Bwv4oc08ONiQ3FiOLKT72Q+ndEMyLNsc/D3qnLMbtUYTQAmkx9E/JRu0DBpHxNddBmNT5hxz1mYBphJ3mfrrw==",
       "cpu": [
         "arm64"
       ],
@@ -358,9 +358,9 @@
       }
     },
     "node_modules/@next/swc-linux-arm64-musl": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.14.tgz",
-      "integrity": "sha512-WgLOA4hT9EIP7jhlkPnvz49iSOMdZgDJVvbpb8WWzJv5wBD07M2wdJXLkDYIpZmCFfo/wPqFsFR4JS4V9KkQ2A==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-arm64-musl/-/swc-linux-arm64-musl-14.2.15.tgz",
+      "integrity": "sha512-k5xf/tg1FBv/M4CMd8S+JL3uV9BnnRmoe7F+GWC3DxkTCD9aewFRH1s5rJ1zkzDa+Do4zyN8qD0N8c84Hu96FQ==",
       "cpu": [
         "arm64"
       ],
@@ -373,9 +373,9 @@
       }
     },
     "node_modules/@next/swc-linux-x64-gnu": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.14.tgz",
-      "integrity": "sha512-lbn7svjUps1kmCettV/R9oAvEW+eUI0lo0LJNFOXoQM5NGNxloAyFRNByYeZKL3+1bF5YE0h0irIJfzXBq9Y6w==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-gnu/-/swc-linux-x64-gnu-14.2.15.tgz",
+      "integrity": "sha512-kE6q38hbrRbKEkkVn62reLXhThLRh6/TvgSP56GkFNhU22TbIrQDEMrO7j0IcQHcew2wfykq8lZyHFabz0oBrA==",
       "cpu": [
         "x64"
       ],
@@ -388,9 +388,9 @@
       }
     },
     "node_modules/@next/swc-linux-x64-musl": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.14.tgz",
-      "integrity": "sha512-7TcQCvLQ/hKfQRgjxMN4TZ2BRB0P7HwrGAYL+p+m3u3XcKTraUFerVbV3jkNZNwDeQDa8zdxkKkw2els/S5onQ==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-linux-x64-musl/-/swc-linux-x64-musl-14.2.15.tgz",
+      "integrity": "sha512-PZ5YE9ouy/IdO7QVJeIcyLn/Rc4ml9M2G4y3kCM9MNf1YKvFY4heg3pVa/jQbMro+tP6yc4G2o9LjAz1zxD7tQ==",
       "cpu": [
         "x64"
       ],
@@ -403,9 +403,9 @@
       }
     },
     "node_modules/@next/swc-win32-arm64-msvc": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.14.tgz",
-      "integrity": "sha512-8i0Ou5XjTLEje0oj0JiI0Xo9L/93ghFtAUYZ24jARSeTMXLUx8yFIdhS55mTExq5Tj4/dC2fJuaT4e3ySvXU1A==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-arm64-msvc/-/swc-win32-arm64-msvc-14.2.15.tgz",
+      "integrity": "sha512-2raR16703kBvYEQD9HNLyb0/394yfqzmIeyp2nDzcPV4yPjqNUG3ohX6jX00WryXz6s1FXpVhsCo3i+g4RUX+g==",
       "cpu": [
         "arm64"
       ],
@@ -418,9 +418,9 @@
       }
     },
     "node_modules/@next/swc-win32-ia32-msvc": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.14.tgz",
-      "integrity": "sha512-2u2XcSaDEOj+96eXpyjHjtVPLhkAFw2nlaz83EPeuK4obF+HmtDJHqgR1dZB7Gb6V/d55FL26/lYVd0TwMgcOQ==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-ia32-msvc/-/swc-win32-ia32-msvc-14.2.15.tgz",
+      "integrity": "sha512-fyTE8cklgkyR1p03kJa5zXEaZ9El+kDNM5A+66+8evQS5e/6v0Gk28LqA0Jet8gKSOyP+OTm/tJHzMlGdQerdQ==",
       "cpu": [
         "ia32"
       ],
@@ -433,9 +433,9 @@
       }
     },
     "node_modules/@next/swc-win32-x64-msvc": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.14.tgz",
-      "integrity": "sha512-MZom+OvZ1NZxuRovKt1ApevjiUJTcU2PmdJKL66xUPaJeRywnbGGRWUlaAOwunD6dX+pm83vj979NTC8QXjGWg==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/@next/swc-win32-x64-msvc/-/swc-win32-x64-msvc-14.2.15.tgz",
+      "integrity": "sha512-SzqGbsLsP9OwKNUG9nekShTwhj6JSB9ZLMWQ8g1gG6hdE5gQLncbnbymrwy2yVmH9nikSLYRYxYMFu78Ggp7/g==",
       "cpu": [
         "x64"
       ],
@@ -990,83 +990,83 @@
       "dev": true
     },
     "node_modules/@sentry-internal/feedback": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry-internal/feedback/-/feedback-7.119.0.tgz",
-      "integrity": "sha512-om8TkAU5CQGO8nkmr7qsSBVkP+/vfeS4JgtW3sjoTK0fhj26+DljR6RlfCGWtYQdPSP6XV7atcPTjbSnsmG9FQ==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry-internal/feedback/-/feedback-7.119.2.tgz",
+      "integrity": "sha512-bnR1yJWVBZfXGx675nMXE8hCXsxluCBfIFy9GQT8PTN/urxpoS9cGz+5F7MA7Xe3Q06/7TT0Mz3fcDvjkqTu3Q==",
       "dependencies": {
-        "@sentry/core": "7.119.0",
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0"
+        "@sentry/core": "7.119.2",
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2"
       },
       "engines": {
         "node": ">=12"
       }
     },
     "node_modules/@sentry-internal/replay-canvas": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry-internal/replay-canvas/-/replay-canvas-7.119.0.tgz",
-      "integrity": "sha512-NL02VQx6ekPxtVRcsdp1bp5Tb5w6vnfBKSIfMKuDRBy5A10Uc3GSoy/c3mPyHjOxB84452A+xZSx6bliEzAnuA==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry-internal/replay-canvas/-/replay-canvas-7.119.2.tgz",
+      "integrity": "sha512-Lqo8IFyeKkdOrOGRqm9jCEqeBl8kINe5+c2VqULpkO/I6ql6ISwPSYnmG6yL8cCVIaT1893CLog/pS4FxCv8/Q==",
       "dependencies": {
-        "@sentry/core": "7.119.0",
-        "@sentry/replay": "7.119.0",
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0"
+        "@sentry/core": "7.119.2",
+        "@sentry/replay": "7.119.2",
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2"
       },
       "engines": {
         "node": ">=12"
       }
     },
     "node_modules/@sentry-internal/tracing": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry-internal/tracing/-/tracing-7.119.0.tgz",
-      "integrity": "sha512-oKdFJnn+56f0DHUADlL8o9l8jTib3VDLbWQBVkjD9EprxfaCwt2m8L5ACRBdQ8hmpxCEo4I8/6traZ7qAdBUqA==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry-internal/tracing/-/tracing-7.119.2.tgz",
+      "integrity": "sha512-V2W+STWrafyGJhQv3ulMFXYDwWHiU6wHQAQBShsHVACiFaDrJ2kPRet38FKv4dMLlLlP2xN+ss2e5zv3tYlTiQ==",
       "dependencies": {
-        "@sentry/core": "7.119.0",
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0"
+        "@sentry/core": "7.119.2",
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2"
       },
       "engines": {
         "node": ">=8"
       }
     },
     "node_modules/@sentry/browser": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry/browser/-/browser-7.119.0.tgz",
-      "integrity": "sha512-WwmW1Y4D764kVGeKmdsNvQESZiAn9t8LmCWO0ucBksrjL2zw9gBPtOpRcO6l064sCLeSxxzCN+kIxhRm1gDFEA==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry/browser/-/browser-7.119.2.tgz",
+      "integrity": "sha512-Wb2RzCsJBTNCmS9KPmbVyV5GGzFXjFdUThAN9xlnN5GgemMBwdQjGu/tRYr8yJAVsRb0EOFH8IuJBNKKNnO49g==",
       "dependencies": {
-        "@sentry-internal/feedback": "7.119.0",
-        "@sentry-internal/replay-canvas": "7.119.0",
-        "@sentry-internal/tracing": "7.119.0",
-        "@sentry/core": "7.119.0",
-        "@sentry/integrations": "7.119.0",
-        "@sentry/replay": "7.119.0",
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0"
+        "@sentry-internal/feedback": "7.119.2",
+        "@sentry-internal/replay-canvas": "7.119.2",
+        "@sentry-internal/tracing": "7.119.2",
+        "@sentry/core": "7.119.2",
+        "@sentry/integrations": "7.119.2",
+        "@sentry/replay": "7.119.2",
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2"
       },
       "engines": {
         "node": ">=8"
       }
     },
     "node_modules/@sentry/core": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry/core/-/core-7.119.0.tgz",
-      "integrity": "sha512-CS2kUv9rAJJEjiRat6wle3JATHypB0SyD7pt4cpX5y0dN5dZ1JrF57oLHRMnga9fxRivydHz7tMTuBhSSwhzjw==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry/core/-/core-7.119.2.tgz",
+      "integrity": "sha512-hQr3d2yWq/2lMvoyBPOwXw1IHqTrCjOsU1vYKhAa6w9vGbJZFGhKGGE2KEi/92c3gqGn+gW/PC7cV6waCTDuVA==",
       "dependencies": {
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0"
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2"
       },
       "engines": {
         "node": ">=8"
       }
     },
     "node_modules/@sentry/integrations": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry/integrations/-/integrations-7.119.0.tgz",
-      "integrity": "sha512-OHShvtsRW0A+ZL/ZbMnMqDEtJddPasndjq+1aQXw40mN+zeP7At/V1yPZyFaURy86iX7Ucxw5BtmzuNy7hLyTA==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry/integrations/-/integrations-7.119.2.tgz",
+      "integrity": "sha512-dCuXKvbUE3gXVVa696SYMjlhSP6CxpMH/gl4Jk26naEB8Xjsn98z/hqEoXLg6Nab73rjR9c/9AdKqBbwVMHyrQ==",
       "dependencies": {
-        "@sentry/core": "7.119.0",
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0",
+        "@sentry/core": "7.119.2",
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2",
         "localforage": "^1.8.1"
       },
       "engines": {
@@ -1074,33 +1074,33 @@
       }
     },
     "node_modules/@sentry/replay": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry/replay/-/replay-7.119.0.tgz",
-      "integrity": "sha512-BnNsYL+X5I4WCH6wOpY6HQtp4MgVt0NVlhLUsEyrvMUiTs0bPkDBrulsgZQBUKJsbOr3l9nHrFoNVB/0i6WNLA==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry/replay/-/replay-7.119.2.tgz",
+      "integrity": "sha512-nHDsBt0mlJXTWAHjzQdCzDbhV2fv8B62PPB5mu5SpI+G5h+ir3r5lR0lZZrMT8eurVowb/HnLXAs+XYVug3blg==",
       "dependencies": {
-        "@sentry-internal/tracing": "7.119.0",
-        "@sentry/core": "7.119.0",
-        "@sentry/types": "7.119.0",
-        "@sentry/utils": "7.119.0"
+        "@sentry-internal/tracing": "7.119.2",
+        "@sentry/core": "7.119.2",
+        "@sentry/types": "7.119.2",
+        "@sentry/utils": "7.119.2"
       },
       "engines": {
         "node": ">=12"
       }
     },
     "node_modules/@sentry/types": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry/types/-/types-7.119.0.tgz",
-      "integrity": "sha512-27qQbutDBPKGbuJHROxhIWc1i0HJaGLA90tjMu11wt0E4UNxXRX+UQl4Twu68v4EV3CPvQcEpQfgsViYcXmq+w==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry/types/-/types-7.119.2.tgz",
+      "integrity": "sha512-ydq1tWsdG7QW+yFaTp0gFaowMLNVikIqM70wxWNK+u98QzKnVY/3XTixxNLsUtnAB4Y+isAzFhrc6Vb5GFdFeg==",
       "engines": {
         "node": ">=8"
       }
     },
     "node_modules/@sentry/utils": {
-      "version": "7.119.0",
-      "resolved": "https://registry.npmjs.org/@sentry/utils/-/utils-7.119.0.tgz",
-      "integrity": "sha512-ZwyXexWn2ZIe2bBoYnXJVPc2esCSbKpdc6+0WJa8eutXfHq3FRKg4ohkfCBpfxljQGEfP1+kfin945lA21Ka+A==",
+      "version": "7.119.2",
+      "resolved": "https://registry.npmjs.org/@sentry/utils/-/utils-7.119.2.tgz",
+      "integrity": "sha512-TLdUCvcNgzKP0r9YD7tgCL1PEUp42TObISridsPJ5rhpVGQJvpr+Six0zIkfDUxerLYWZoK8QMm9KgFlPLNQzA==",
       "dependencies": {
-        "@sentry/types": "7.119.0"
+        "@sentry/types": "7.119.2"
       },
       "engines": {
         "node": ">=8"
@@ -1151,9 +1151,9 @@
       "dev": true
     },
     "node_modules/@types/node": {
-      "version": "20.16.10",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-20.16.10.tgz",
-      "integrity": "sha512-vQUKgWTjEIRFCvK6CyriPH3MZYiYlNy0fKiEYHWbcoWLEgs4opurGGKlebrTLqdSMIbXImH6XExNiIyNUv3WpA==",
+      "version": "20.16.13",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-20.16.13.tgz",
+      "integrity": "sha512-GjQ7im10B0labo8ZGXDGROUl9k0BNyDgzfGpb4g/cl+4yYDWVKcozANF4FGr4/p0O/rAkQClM6Wiwkije++1Tg==",
       "dev": true,
       "dependencies": {
         "undici-types": "~6.19.2"
@@ -1176,9 +1176,9 @@
       }
     },
     "node_modules/@types/react-dom": {
-      "version": "18.3.0",
-      "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.0.tgz",
-      "integrity": "sha512-EhwApuTmMBmXuFOikhQLIBUn6uFg81SwLMOAUgodJF14SOBOCMdU04gDoYi0WOJJHD144TL32z4yDqCW3dnkQg==",
+      "version": "18.3.1",
+      "resolved": "https://registry.npmjs.org/@types/react-dom/-/react-dom-18.3.1.tgz",
+      "integrity": "sha512-qW1Mfv8taImTthu4KoXgDfLuk4bydU6Q/TkADnDWWHwi4NX4BR+LWfTp2sVmTqRrsHvyDDTelgelxJ+SsejKKQ==",
       "devOptional": true,
       "dependencies": {
         "@types/react": "*"
@@ -1318,9 +1318,9 @@
       "dev": true
     },
     "node_modules/acorn": {
-      "version": "8.12.1",
-      "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.12.1.tgz",
-      "integrity": "sha512-tcpGyI9zbizT9JbV6oYE477V6mTlXvvi0T0G3SNIYE2apm/G5huBa1+K89VGeovbg+jycCrfhl3ADxErOuO6Jg==",
+      "version": "8.13.0",
+      "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.13.0.tgz",
+      "integrity": "sha512-8zSiw54Oxrdym50NlZ9sUusyO1Z1ZchgRLWRaK6c86XJFClyCgFKetdowBg5bKxyp/u+CDBJG4Mpp0m3HLZl9w==",
       "dev": true,
       "bin": {
         "acorn": "bin/acorn"
@@ -1642,9 +1642,9 @@
       }
     },
     "node_modules/axe-core": {
-      "version": "4.10.0",
-      "resolved": "https://registry.npmjs.org/axe-core/-/axe-core-4.10.0.tgz",
-      "integrity": "sha512-Mr2ZakwQ7XUAjp7pAwQWRhhK8mQQ6JAaNWSjmjxil0R8BPioMtQsTLOolGYkji1rcL++3dCqZA3zWqpT+9Ew6g==",
+      "version": "4.10.1",
+      "resolved": "https://registry.npmjs.org/axe-core/-/axe-core-4.10.1.tgz",
+      "integrity": "sha512-qPC9o+kD8Tir0lzNGLeghbOrWMr3ZJpaRlCIb6Uobt/7N4FiEDvqUMnxzCHRHmg8vOg14kr5gVNyScRmbMaJ9g==",
       "dev": true,
       "engines": {
         "node": ">=4"
@@ -1781,9 +1781,9 @@
       }
     },
     "node_modules/caniuse-lite": {
-      "version": "1.0.30001666",
-      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001666.tgz",
-      "integrity": "sha512-gD14ICmoV5ZZM1OdzPWmpx+q4GyefaK06zi8hmfHV5xe4/2nOQX3+Dw5o+fSqOws2xVwL9j+anOPFwHzdEdV4g==",
+      "version": "1.0.30001669",
+      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001669.tgz",
+      "integrity": "sha512-DlWzFDJqstqtIVx1zeSpIMLjunf5SmwOw0N2Ck/QSQdS8PLS4+9HrLaYei4w8BIAL7IB/UEDu889d8vhCTPA0w==",
       "funding": [
         {
           "type": "opencollective",
@@ -2140,9 +2140,9 @@
       "integrity": "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA=="
     },
     "node_modules/electron-to-chromium": {
-      "version": "1.5.31",
-      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.31.tgz",
-      "integrity": "sha512-QcDoBbQeYt0+3CWcK/rEbuHvwpbT/8SV9T3OSgs6cX1FlcUAkgrkqbg9zLnDrMM/rLamzQwal4LYFCiWk861Tg==",
+      "version": "1.5.41",
+      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.41.tgz",
+      "integrity": "sha512-dfdv/2xNjX0P8Vzme4cfzHqnPm5xsZXwsolTYr0eyW18IUmNyG08vL+fttvinTfhKfIKdRoqkDIC9e9iWQCNYQ==",
       "dev": true
     },
     "node_modules/emoji-regex": {
@@ -2265,9 +2265,9 @@
       }
     },
     "node_modules/es-iterator-helpers": {
-      "version": "1.0.19",
-      "resolved": "https://registry.npmjs.org/es-iterator-helpers/-/es-iterator-helpers-1.0.19.tgz",
-      "integrity": "sha512-zoMwbCcH5hwUkKJkT8kDIBZSz9I6mVG//+lDCinLCGov4+r7NIy0ld8o03M0cJxl2spVf6ESYVS6/gpIfq1FFw==",
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/es-iterator-helpers/-/es-iterator-helpers-1.1.0.tgz",
+      "integrity": "sha512-/SurEfycdyssORP/E+bj4sEu1CWw4EmLDsHynHwSXQ7utgbrMRWW195pTrCjFgFCddf/UkYm3oqKPRq5i8bJbw==",
       "dev": true,
       "dependencies": {
         "call-bind": "^1.0.7",
@@ -2277,12 +2277,12 @@
         "es-set-tostringtag": "^2.0.3",
         "function-bind": "^1.1.2",
         "get-intrinsic": "^1.2.4",
-        "globalthis": "^1.0.3",
+        "globalthis": "^1.0.4",
         "has-property-descriptors": "^1.0.2",
         "has-proto": "^1.0.3",
         "has-symbols": "^1.0.3",
         "internal-slot": "^1.0.7",
-        "iterator.prototype": "^1.1.2",
+        "iterator.prototype": "^1.1.3",
         "safe-array-concat": "^1.1.2"
       },
       "engines": {
@@ -2366,6 +2366,7 @@
       "version": "8.57.1",
       "resolved": "https://registry.npmjs.org/eslint/-/eslint-8.57.1.tgz",
       "integrity": "sha512-ypowyDxpVSYpkXr9WPv2PAZCtNip1Mv5KTW0SCurXv/9iOpcrH9PaqUElksqEB6pChqHGDRCFTyrZlGhnLNGiA==",
+      "deprecated": "This version is no longer supported. Please see https://eslint.org/version-support for other options.",
       "dev": true,
       "dependencies": {
         "@eslint-community/eslint-utils": "^4.2.0",
@@ -2525,9 +2526,9 @@
       }
     },
     "node_modules/eslint-plugin-import": {
-      "version": "2.30.0",
-      "resolved": "https://registry.npmjs.org/eslint-plugin-import/-/eslint-plugin-import-2.30.0.tgz",
-      "integrity": "sha512-/mHNE9jINJfiD2EKkg1BKyPyUk4zdnT54YgbOgfjSakWT5oyX/qQLVNTkehyfpcMxZXMy1zyonZ2v7hZTX43Yw==",
+      "version": "2.31.0",
+      "resolved": "https://registry.npmjs.org/eslint-plugin-import/-/eslint-plugin-import-2.31.0.tgz",
+      "integrity": "sha512-ixmkI62Rbc2/w8Vfxyh1jQRTdRTF52VxwRVHl/ykPAmqG+Nb7/kNn+byLP0LxPgI7zWA16Jt82SybJInmMia3A==",
       "dev": true,
       "dependencies": {
         "@rtsao/scc": "^1.1.0",
@@ -2538,7 +2539,7 @@
         "debug": "^3.2.7",
         "doctrine": "^2.1.0",
         "eslint-import-resolver-node": "^0.3.9",
-        "eslint-module-utils": "^2.9.0",
+        "eslint-module-utils": "^2.12.0",
         "hasown": "^2.0.2",
         "is-core-module": "^2.15.1",
         "is-glob": "^4.0.3",
@@ -2547,13 +2548,14 @@
         "object.groupby": "^1.0.3",
         "object.values": "^1.2.0",
         "semver": "^6.3.1",
+        "string.prototype.trimend": "^1.0.8",
         "tsconfig-paths": "^3.15.0"
       },
       "engines": {
         "node": ">=4"
       },
       "peerDependencies": {
-        "eslint": "^2 || ^3 || ^4 || ^5 || ^6 || ^7.2.0 || ^8"
+        "eslint": "^2 || ^3 || ^4 || ^5 || ^6 || ^7.2.0 || ^8 || ^9"
       }
     },
     "node_modules/eslint-plugin-import/node_modules/debug": {
@@ -2649,9 +2651,9 @@
       }
     },
     "node_modules/eslint-plugin-react-hooks": {
-      "version": "4.6.2",
-      "resolved": "https://registry.npmjs.org/eslint-plugin-react-hooks/-/eslint-plugin-react-hooks-4.6.2.tgz",
-      "integrity": "sha512-QzliNJq4GinDBcD8gPB5v0wh6g8q3SUi6EFF0x8N/BL9PoVs0atuGc47ozMRyOWAKdwaZ5OnbOEa3WR+dSGKuQ==",
+      "version": "5.0.0-canary-7118f5dd7-20230705",
+      "resolved": "https://registry.npmjs.org/eslint-plugin-react-hooks/-/eslint-plugin-react-hooks-5.0.0-canary-7118f5dd7-20230705.tgz",
+      "integrity": "sha512-AZYbMo/NW9chdL7vk6HQzQhT+PvTAEVqWk9ziruUoW2kAOcN5qNyelv70e0F1VNQAbvutOC9oc+xfWycI9FxDw==",
       "dev": true,
       "engines": {
         "node": ">=10"
@@ -2941,9 +2943,9 @@
       }
     },
     "node_modules/framer-motion": {
-      "version": "11.9.0",
-      "resolved": "https://registry.npmjs.org/framer-motion/-/framer-motion-11.9.0.tgz",
-      "integrity": "sha512-nCfGxvsQecVLjjYDu35G2F5ls+ArE3FBfhxV0RSiisMaUKqteq5DMBFNRKwMyVj+VqKTNhawt+BV480YCHKFlQ==",
+      "version": "11.11.9",
+      "resolved": "https://registry.npmjs.org/framer-motion/-/framer-motion-11.11.9.tgz",
+      "integrity": "sha512-XpdZseuCrZehdHGuW22zZt3SF5g6AHJHJi7JwQIigOznW4Jg1n0oGPMJQheMaKLC+0rp5gxUKMRYI6ytd3q4RQ==",
       "dependencies": {
         "tslib": "^2.4.0"
       },
@@ -3766,9 +3768,9 @@
       "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="
     },
     "node_modules/iterator.prototype": {
-      "version": "1.1.2",
-      "resolved": "https://registry.npmjs.org/iterator.prototype/-/iterator.prototype-1.1.2.tgz",
-      "integrity": "sha512-DR33HMMr8EzwuRL8Y9D3u2BMj8+RqSE850jfGu59kS7tbmPLzGkZmVSfyCFSDxuZiEY6Rzt3T2NA/qU+NwVj1w==",
+      "version": "1.1.3",
+      "resolved": "https://registry.npmjs.org/iterator.prototype/-/iterator.prototype-1.1.3.tgz",
+      "integrity": "sha512-FW5iMbeQ6rBGm/oKgzq2aW4KvAGpxPzYES8N4g4xNXUKpL1mclMvOe+76AcLDTvD+Ze+sOpVhgdAQEKF4L9iGQ==",
       "dev": true,
       "dependencies": {
         "define-properties": "^1.2.1",
@@ -3776,6 +3778,9 @@
         "has-symbols": "^1.0.3",
         "reflect.getprototypeof": "^1.0.4",
         "set-function-name": "^2.0.1"
+      },
+      "engines": {
+        "node": ">= 0.4"
       }
     },
     "node_modules/jackspeak": {
@@ -4065,11 +4070,11 @@
       "dev": true
     },
     "node_modules/next": {
-      "version": "14.2.14",
-      "resolved": "https://registry.npmjs.org/next/-/next-14.2.14.tgz",
-      "integrity": "sha512-Q1coZG17MW0Ly5x76shJ4dkC23woLAhhnDnw+DfTc7EpZSGuWrlsZ3bZaO8t6u1Yu8FVfhkqJE+U8GC7E0GLPQ==",
+      "version": "14.2.15",
+      "resolved": "https://registry.npmjs.org/next/-/next-14.2.15.tgz",
+      "integrity": "sha512-h9ctmOokpoDphRvMGnwOJAedT6zKhwqyZML9mDtspgf4Rh3Pn7UTYKqePNoDvhsWBAO5GoPNYshnAUGIazVGmw==",
       "dependencies": {
-        "@next/env": "14.2.14",
+        "@next/env": "14.2.15",
         "@swc/helpers": "0.5.5",
         "busboy": "1.6.0",
         "caniuse-lite": "^1.0.30001579",
@@ -4084,15 +4089,15 @@
         "node": ">=18.17.0"
       },
       "optionalDependencies": {
-        "@next/swc-darwin-arm64": "14.2.14",
-        "@next/swc-darwin-x64": "14.2.14",
-        "@next/swc-linux-arm64-gnu": "14.2.14",
-        "@next/swc-linux-arm64-musl": "14.2.14",
-        "@next/swc-linux-x64-gnu": "14.2.14",
-        "@next/swc-linux-x64-musl": "14.2.14",
-        "@next/swc-win32-arm64-msvc": "14.2.14",
-        "@next/swc-win32-ia32-msvc": "14.2.14",
-        "@next/swc-win32-x64-msvc": "14.2.14"
+        "@next/swc-darwin-arm64": "14.2.15",
+        "@next/swc-darwin-x64": "14.2.15",
+        "@next/swc-linux-arm64-gnu": "14.2.15",
+        "@next/swc-linux-arm64-musl": "14.2.15",
+        "@next/swc-linux-x64-gnu": "14.2.15",
+        "@next/swc-linux-x64-musl": "14.2.15",
+        "@next/swc-win32-arm64-msvc": "14.2.15",
+        "@next/swc-win32-ia32-msvc": "14.2.15",
+        "@next/swc-win32-x64-msvc": "14.2.15"
       },
       "peerDependencies": {
         "@opentelemetry/api": "^1.1.0",
@@ -4421,9 +4426,9 @@
       }
     },
     "node_modules/picocolors": {
-      "version": "1.1.0",
-      "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.0.tgz",
-      "integrity": "sha512-TQ92mBOW0l3LeMeyLV6mzy/kWr8lkd/hp3mTg7wYK7zJhuBStmGMBG0BdeDZS/dZx1IukaX6Bk11zcln25o1Aw=="
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
+      "integrity": "sha512-xceH2snhtb5M9liqDsmEw56le376mTZkEX/jEb/RxNFyegNul7eNslCXP9FDj/Lcu0X8KEyMceP2ntpaHrDEVA=="
     },
     "node_modules/picomatch": {
       "version": "2.3.1",
@@ -4817,15 +4822,15 @@
       "integrity": "sha512-dYnhHh0nJoMfnkZs6GmmhFknAGRrLznOu5nc9ML+EJxGvrx6H7teuevqVqCuPcPK//3eDrrjQhehXVx9cnkGdw=="
     },
     "node_modules/regexp.prototype.flags": {
-      "version": "1.5.2",
-      "resolved": "https://registry.npmjs.org/regexp.prototype.flags/-/regexp.prototype.flags-1.5.2.tgz",
-      "integrity": "sha512-NcDiDkTLuPR+++OCKB0nWafEmhg/Da8aUPLPMQbK+bxKKCm1/S5he+AqYa4PlMCVBalb4/yxIRub6qkEx5yJbw==",
+      "version": "1.5.3",
+      "resolved": "https://registry.npmjs.org/regexp.prototype.flags/-/regexp.prototype.flags-1.5.3.tgz",
+      "integrity": "sha512-vqlC04+RQoFalODCbCumG2xIOvapzVMHwsyIGM/SIE8fRhFFsXeH8/QQ+s0T0kDAhKc4k30s73/0ydkHQz6HlQ==",
       "dev": true,
       "dependencies": {
-        "call-bind": "^1.0.6",
+        "call-bind": "^1.0.7",
         "define-properties": "^1.2.1",
         "es-errors": "^1.3.0",
-        "set-function-name": "^2.0.1"
+        "set-function-name": "^2.0.2"
       },
       "engines": {
         "node": ">= 0.4"
@@ -5169,13 +5174,17 @@
       }
     },
     "node_modules/string.prototype.includes": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/string.prototype.includes/-/string.prototype.includes-2.0.0.tgz",
-      "integrity": "sha512-E34CkBgyeqNDcrbU76cDjL5JLcVrtSdYq0MEh/B10r17pRP4ciHLwTgnuLV8Ay6cgEMLkcBkFCKyFZ43YldYzg==",
+      "version": "2.0.1",
+      "resolved": "https://registry.npmjs.org/string.prototype.includes/-/string.prototype.includes-2.0.1.tgz",
+      "integrity": "sha512-o7+c9bW6zpAdJHTtujeePODAhkuicdAryFsfVKwA+wGw89wJ4GTY484WTucM9hLtDEOpOvI+aHnzqnC5lHp4Rg==",
       "dev": true,
       "dependencies": {
-        "define-properties": "^1.1.3",
-        "es-abstract": "^1.17.5"
+        "call-bind": "^1.0.7",
+        "define-properties": "^1.2.1",
+        "es-abstract": "^1.23.3"
+      },
+      "engines": {
+        "node": ">= 0.4"
       }
     },
     "node_modules/string.prototype.matchall": {
@@ -5374,18 +5383,18 @@
       }
     },
     "node_modules/tailwind-merge": {
-      "version": "2.5.2",
-      "resolved": "https://registry.npmjs.org/tailwind-merge/-/tailwind-merge-2.5.2.tgz",
-      "integrity": "sha512-kjEBm+pvD+6eAwzJL2Bi+02/9LFLal1Gs61+QB7HvTfQQ0aXwC5LGT8PEt1gS0CWKktKe6ysPTAy3cBC5MeiIg==",
+      "version": "2.5.4",
+      "resolved": "https://registry.npmjs.org/tailwind-merge/-/tailwind-merge-2.5.4.tgz",
+      "integrity": "sha512-0q8cfZHMu9nuYP/b5Shb7Y7Sh1B7Nnl5GqNr1U+n2p6+mybvRtayrQ+0042Z5byvTA8ihjlP8Odo8/VnHbZu4Q==",
       "funding": {
         "type": "github",
         "url": "https://github.com/sponsors/dcastil"
       }
     },
     "node_modules/tailwindcss": {
-      "version": "3.4.13",
-      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.13.tgz",
-      "integrity": "sha512-KqjHOJKogOUt5Bs752ykCeiwvi0fKVkr5oqsFNt/8px/tA8scFPIlkygsf6jXrfCqGHz7VflA6+yytWuM+XhFw==",
+      "version": "3.4.14",
+      "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.14.tgz",
+      "integrity": "sha512-IcSvOcTRcUtQQ7ILQL5quRDg7Xs93PdJEk1ZLbhhvJc7uj/OAhYOnruEiwnGgBvUtaUAJ8/mhSw1o8L2jCiENA==",
       "dependencies": {
         "@alloc/quick-lru": "^5.2.0",
         "arg": "^5.0.2",
@@ -5501,9 +5510,9 @@
       }
     },
     "node_modules/tslib": {
-      "version": "2.7.0",
-      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.7.0.tgz",
-      "integrity": "sha512-gLXCKdN1/j47AiHiOkJN69hJmcbGTHI0ImLmbYLHykhgeN0jVGola9yVjFgzCUklsZQMW55o+dW7IXv3RCXDzA=="
+      "version": "2.8.0",
+      "resolved": "https://registry.npmjs.org/tslib/-/tslib-2.8.0.tgz",
+      "integrity": "sha512-jWVzBLplnCmoaTr13V9dYbiQ99wvZRd0vNWaDRg+aVYRcjDF3nDksxFDE/+fkXnKhpnUUkmx5pK/v8mCtLVqZA=="
     },
     "node_modules/type-check": {
       "version": "0.4.0",
@@ -5603,9 +5612,9 @@
       }
     },
     "node_modules/typescript": {
-      "version": "5.6.2",
-      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.6.2.tgz",
-      "integrity": "sha512-NW8ByodCSNCwZeghjN3o+JX5OFH0Ojg6sadjEKY4huZ52TqbJTJnDo5+Tw98lSy63NZvi4n+ez5m2u5d4PkZyw==",
+      "version": "5.6.3",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.6.3.tgz",
+      "integrity": "sha512-hjcS1mhfuyi4WW8IWtjP7brDrG2cuDZukyrYrSauoXGNgx0S7zceP07adYkJycEr56BOUTNPzbInooiN3fn1qw==",
       "dev": true,
       "bin": {
         "tsc": "bin/tsc",
@@ -5917,9 +5926,9 @@
       "dev": true
     },
     "node_modules/yaml": {
-      "version": "2.5.1",
-      "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.5.1.tgz",
-      "integrity": "sha512-bLQOjaX/ADgQ20isPJRvF0iRUHIxVhYvr53Of7wGcWlO2jvtUlH5m87DsmulFVxRpNLOnI4tB6p/oh8D7kpn9Q==",
+      "version": "2.6.0",
+      "resolved": "https://registry.npmjs.org/yaml/-/yaml-2.6.0.tgz",
+      "integrity": "sha512-a6ae//JvKDEra2kdi1qzCyrJW/WZCgFi8ydDV+eXExl95t+5R+ijnqHJbz9tmMh8FUjx3iv2fCQ4dclAQlO2UQ==",
       "bin": {
         "yaml": "bin.mjs"
       },

examples/storytelling-chatbot/frontend/package.json

@@ -17,7 +17,7 @@
     "class-variance-authority": "^0.7.0",
     "clsx": "^2.1.1",
     "framer-motion": "^11.9.0",
-    "next": "^14.2.14",
+    "next": "^14.2.15",
     "react": "^18.3.1",
     "react-dom": "^18.3.1",
     "recoil": "^0.7.7",

examples/storytelling-chatbot/src/bot.py

@@ -1,18 +1,20 @@
 import argparse
 import asyncio
-import aiohttp
 import os
 import sys
 
+import aiohttp
+from dotenv import load_dotenv
+from loguru import logger
+from processors import StoryImageProcessor, StoryProcessor
+from prompts import CUE_USER_TURN, LLM_BASE_PROMPT, LLM_INTRO_PROMPT
+from utils.helpers import load_images, load_sounds
 
-from pipecat.frames.frames import LLMMessagesFrame, StopTaskFrame, EndFrame
+from pipecat.frames.frames import EndFrame, LLMMessagesFrame, StopTaskFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.elevenlabs import ElevenLabsTTSService
 from pipecat.services.fal import FalImageGenService
 from pipecat.services.openai import OpenAILLMService
@@ -22,14 +24,6 @@ from pipecat.transports.services.daily import (
     DailyTransportMessageFrame,
 )
 
-from processors import StoryProcessor, StoryImageProcessor
-from prompts import LLM_BASE_PROMPT, LLM_INTRO_PROMPT, CUE_USER_TURN
-from utils.helpers import load_sounds, load_images
-
-from loguru import logger
-
-from dotenv import load_dotenv
-
 load_dotenv(override=True)
 
 logger.remove(0)
@@ -85,8 +79,8 @@ async def main(room_url, token=None):
         story_pages = []
 
         # We need aggregators to keep track of user and LLM responses
-        llm_responses = LLMAssistantResponseAggregator(message_history)
-        user_responses = LLMUserResponseAggregator(message_history)
+        context = OpenAILLMContext(message_history)
+        context_aggregator = llm_service.create_context_aggregator(context)
 
         # -------------- Processors ------------- #
 
@@ -108,7 +102,7 @@ async def main(room_url, token=None):
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
             logger.debug("Participant joined, storytime commence!")
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             await intro_task.queue_frames(
                 [
                     images["book1"],
@@ -129,13 +123,13 @@ async def main(room_url, token=None):
         main_pipeline = Pipeline(
             [
                 transport.input(),
-                user_responses,
+                context_aggregator.user(),
                 llm_service,
                 story_processor,
                 image_processor,
                 tts_service,
                 transport.output(),
-                llm_responses,
+                context_aggregator.assistant(),
             ]
         )
 

examples/storytelling-chatbot/src/bot_runner.py

@@ -69,7 +69,7 @@ STATIC_DIR = "frontend/out"
 app.mount("/static", StaticFiles(directory=STATIC_DIR, html=True), name="static")
 
 
-@app.post("/start_bot")
+@app.post("/")
 async def start_bot(request: Request) -> JSONResponse:
     if os.getenv("ENV", "dev") == "production":
         # Only allow requests from the specified domain

examples/studypal/studypal.py

@@ -8,18 +8,15 @@ from bs4 import BeautifulSoup
 from pypdf import PdfReader
 import tiktoken
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from runner import configure
 
@@ -150,17 +147,17 @@ Your task is to help the user understand and learn from this article in 2 senten
             },
         ]
 
-        tma_in = LLMUserResponseAggregator(messages)
-        tma_out = LLMAssistantResponseAggregator(messages)
+        context = OpenAILLMContext(messages)
+        context_aggregator = llm.create_context_aggregator(context)
 
         pipeline = Pipeline(
             [
                 transport.input(),
-                tma_in,
+                context_aggregator.user(),
                 llm,
                 tts,
                 transport.output(),
-                tma_out,
+                context_aggregator.assistant(),
             ]
         )
 
@@ -168,7 +165,7 @@ Your task is to help the user understand and learn from this article in 2 senten
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
             messages.append(
                 {
                     "role": "system",

examples/translation-chatbot/README.md

@@ -23,7 +23,7 @@ cp env.example .env # and add your credentials
 python server.py
 ```
 
-Then, visit `http://localhost:7860/start` in your browser to start a translatorbot session.
+Then, visit `http://localhost:7860/` in your browser to start a translatorbot session.
 
 ## Build and test the Docker image
 

examples/translation-chatbot/bot.py

@@ -121,7 +121,7 @@ async def main():
 
         @transport.event_handler("on_first_participant_joined")
         async def on_first_participant_joined(transport, participant):
-            transport.capture_participant_transcription(participant["id"])
+            await transport.capture_participant_transcription(participant["id"])
 
         runner = PipelineRunner()
 

examples/translation-chatbot/server.py

@@ -57,7 +57,7 @@ app.add_middleware(
 )
 
 
-@app.get("/start")
+@app.get("/")
 async def start_agent(request: Request):
     print(f"!!! Creating room")
     room = await daily_helpers["rest"].create_room(DailyRoomParams())

examples/twilio-chatbot/README.md

@@ -53,7 +53,7 @@ This project is a FastAPI-based chatbot that integrates with Twilio to handle We
     ```
 
 2. **Update the Twilio Webhook**:
-    Copy the ngrok URL and update your Twilio phone number webhook URL to `http://<ngrok_url>/start_call`.
+    Copy the ngrok URL and update your Twilio phone number webhook URL to `http://<ngrok_url>/`.
 
 3. **Update streams.xml**:
     Copy the ngrok URL and update templates/streams.xml with `wss://<ngrok_url>/ws`.

examples/twilio-chatbot/bot.py

@@ -1,14 +1,12 @@
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import EndFrame, LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.services.deepgram import DeepgramSTTService
@@ -16,7 +14,6 @@ from pipecat.transports.network.fastapi_websocket import (
     FastAPIWebsocketTransport,
     FastAPIWebsocketParams,
 )
-from pipecat.vad.silero import SileroVADAnalyzer
 from pipecat.serializers.twilio import TwilioFrameSerializer
 
 from loguru import logger
@@ -58,18 +55,18 @@ async def run_bot(websocket_client, stream_sid):
         },
     ]
 
-    tma_in = LLMUserResponseAggregator(messages)
-    tma_out = LLMAssistantResponseAggregator(messages)
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
 
     pipeline = Pipeline(
         [
             transport.input(),  # Websocket input from client
             stt,  # Speech-To-Text
-            tma_in,  # User responses
+            context_aggregator.user(),
             llm,  # LLM
             tts,  # Text-To-Speech
             transport.output(),  # Websocket output to client
-            tma_out,  # LLM responses
+            context_aggregator.assistant(),
         ]
     )
 

examples/twilio-chatbot/server.py

@@ -19,7 +19,7 @@ app.add_middleware(
 )
 
 
-@app.post("/start_call")
+@app.post("/")
 async def start_call():
     print("POST TwiML")
     return HTMLResponse(content=open("templates/streams.xml").read(), media_type="application/xml")

examples/websocket-server/bot.py

@@ -8,14 +8,12 @@ import asyncio
 import os
 import sys
 
+from pipecat.audio.vad.silero import SileroVADAnalyzer
 from pipecat.frames.frames import LLMMessagesFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineTask
-from pipecat.processors.aggregators.llm_response import (
-    LLMAssistantResponseAggregator,
-    LLMUserResponseAggregator,
-)
+from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
@@ -23,7 +21,6 @@ from pipecat.transports.network.websocket_server import (
     WebsocketServerParams,
     WebsocketServerTransport,
 )
-from pipecat.vad.silero import SileroVADAnalyzer
 
 from loguru import logger
 
@@ -62,18 +59,18 @@ async def main():
         },
     ]
 
-    tma_in = LLMUserResponseAggregator(messages)
-    tma_out = LLMAssistantResponseAggregator(messages)
+    context = OpenAILLMContext(messages)
+    context_aggregator = llm.create_context_aggregator(context)
 
     pipeline = Pipeline(
         [
             transport.input(),  # Websocket input from client
             stt,  # Speech-To-Text
-            tma_in,  # User responses
+            context_aggregator.user(),
             llm,  # LLM
             tts,  # Text-To-Speech
             transport.output(),  # Websocket output to client
-            tma_out,  # LLM responses
+            context_aggregator.assistant(),
         ]
     )
 

pyproject.toml

@@ -21,13 +21,14 @@ classifiers = [
 ]
 dependencies = [
     "aiohttp~=3.10.3",
+    "loguru~=0.7.2",
     "Markdown~=3.7",
     "numpy~=1.26.4",
-    "loguru~=0.7.2",
     "Pillow~=10.4.0",
     "protobuf~=4.25.4",
     "pydantic~=2.8.2",
     "pyloudnorm~=0.1.1",
+    "resampy~=0.4.3",
 ]
 
 [project.urls]
@@ -36,32 +37,32 @@ Website = "https://pipecat.ai"
 
 [project.optional-dependencies]
 anthropic = [ "anthropic~=0.34.0" ]
+assemblyai = [ "assemblyai~=0.34.0" ]
 aws = [ "boto3~=1.35.27" ]
 azure = [ "azure-cognitiveservices-speech~=1.40.0" ]
 canonical = [ "aiofiles~=24.1.0" ]
-cartesia = [ "cartesia~=1.0.13", "websockets~=12.0" ]
-daily = [ "daily-python~=0.11.0" ]
+cartesia = [ "cartesia~=1.0.13", "websockets~=13.1" ]
+daily = [ "daily-python~=0.12.0" ]
 deepgram = [ "deepgram-sdk~=3.7.3" ]
-elevenlabs = [ "websockets~=12.0" ]
+elevenlabs = [ "websockets~=13.1" ]
 examples = [ "python-dotenv~=1.0.1", "flask~=3.0.3", "flask_cors~=4.0.1" ]
 fal = [ "fal-client~=0.4.1" ]
-gladia = [ "websockets~=12.0" ]
-google = [ "google-generativeai~=0.7.2", "google-cloud-texttospeech~=2.17.2" ]
+gladia = [ "websockets~=13.1" ]
+google = [ "google-generativeai~=0.8.3", "google-cloud-texttospeech~=2.17.2" ]
 gstreamer = [ "pygobject~=3.48.2" ]
 fireworks = [ "openai~=1.37.2" ]
 langchain = [ "langchain~=0.2.14", "langchain-community~=0.2.12", "langchain-openai~=0.1.20" ]
-livekit = [ "livekit~=0.13.1", "tenacity~=9.0.0" ]
+livekit = [ "livekit~=0.17.5", "livekit-api~=0.7.1", "tenacity~=8.5.0" ]
 lmnt = [ "lmnt~=1.1.4" ]
 local = [ "pyaudio~=0.2.14" ]
 moondream = [ "einops~=0.8.0", "timm~=1.0.8", "transformers~=4.44.0" ]
-openai = [ "openai~=1.50.2", "websockets~=12.0", "python-deepcompare~=1.0.1" ]
+openai = [ "openai~=1.50.2", "websockets~=13.1", "python-deepcompare~=1.0.1" ]
 openpipe = [ "openpipe~=4.24.0" ]
-playht = [ "pyht~=0.0.28" ]
-silero = [ "onnxruntime>=1.16.1" ]
+playht = [ "pyht~=0.1.4", "websockets~=13.1" ]
+silero = [ "onnxruntime~=1.19.2" ]
 together = [ "openai~=1.50.2" ]
-websocket = [ "websockets~=12.0", "fastapi~=0.115.0" ]
+websocket = [ "websockets~=13.1", "fastapi~=0.115.0" ]
 whisper = [ "faster-whisper~=1.0.3" ]
-xtts = [ "resampy~=0.4.3" ]
 
 [tool.setuptools.packages.find]
 # All the following settings are optional:
@@ -73,3 +74,7 @@ pythonpath = ["src"]
 [tool.setuptools_scm]
 local_scheme = "no-local-version"
 fallback_version = "0.0.0-dev"
+
+[tool.ruff]
+exclude = ["*_pb2.py"]
+line-length = 100

src/pipecat/audio/utils.py

@@ -7,6 +7,15 @@
 import audioop
 import numpy as np
 import pyloudnorm as pyln
+import resampy
+
+
+def resample_audio(audio: bytes, original_rate: int, target_rate: int) -> bytes:
+    if original_rate == target_rate:
+        return audio
+    audio_data = np.frombuffer(audio, dtype=np.int16)
+    resampled_audio = resampy.resample(audio_data, original_rate, target_rate)
+    return resampled_audio.astype(np.int16).tobytes()
 
 
 def normalize_value(value, min_value, max_value):